The objective was to measure the effect of various face masks on speech recognition threshold and the word recognition score in the presence of varying background noise levels.20 normal-hearing adult subjects(a total ...The objective was to measure the effect of various face masks on speech recognition threshold and the word recognition score in the presence of varying background noise levels.20 normal-hearing adult subjects(a total of 40 ears)participated.Pure tone audiometry followed by speech recognition threshold and word recognition score at the most comfortable level in varying signal-to-noise ratios(SNR0,SNR10,and SNR15)using surgical,pleated cloth,and N95 masks.Using surgical,cloth,and N95 masks,speech recognition thresholds increased by 1.8 dB,4.4 dB,and 5.05 dB,respectively.Word recognition scores decreased by 32%without a mask,43.7%in a surgical mask,46.3%in a cloth mask,and 46.7%in N95 mask conditions,between SNR15 and SNR0.The speech recognition threshold was negatively affected with cloth and N95 masks.Surgical masks do not affect the word recognition scores at lower background noise levels.However,as the signal-to-noise ratio decreased,even the surgical,cloth,and N95 masks significantly impacted the word recognition score even in normal-hearing individuals.展开更多
Large Language Models(LLMs)are increasingly demonstrating their ability to understand natural language and solve complex tasks,especially through text generation.One of the relevant capabilities is contextual learning...Large Language Models(LLMs)are increasingly demonstrating their ability to understand natural language and solve complex tasks,especially through text generation.One of the relevant capabilities is contextual learning,which involves the ability to receive instructions in natural language or task demonstrations to generate expected outputs for test instances without the need for additional training or gradient updates.In recent years,the popularity of social networking has provided a medium through which some users can engage in offensive and harmful online behavior.In this study,we investigate the ability of different LLMs,ranging from zero-shot and few-shot learning to fine-tuning.Our experiments show that LLMs can identify sexist and hateful online texts using zero-shot and few-shot approaches through information retrieval.Furthermore,it is found that the encoder-decoder model called Zephyr achieves the best results with the fine-tuning approach,scoring 86.811%on the Explainable Detection of Online Sexism(EDOS)test-set and 57.453%on the Multilingual Detection of Hate Speech Against Immigrants and Women in Twitter(HatEval)test-set.Finally,it is confirmed that the evaluated models perform well in hate text detection,as they beat the best result in the HatEval task leaderboard.The error analysis shows that contextual learning had difficulty distinguishing between types of hate speech and figurative language.However,the fine-tuned approach tends to produce many false positives.展开更多
Detecting hate speech automatically in social media forensics has emerged as a highly challenging task due tothe complex nature of language used in such platforms. Currently, several methods exist for classifying hate...Detecting hate speech automatically in social media forensics has emerged as a highly challenging task due tothe complex nature of language used in such platforms. Currently, several methods exist for classifying hatespeech, but they still suffer from ambiguity when differentiating between hateful and offensive content and theyalso lack accuracy. The work suggested in this paper uses a combination of the Whale Optimization Algorithm(WOA) and Particle Swarm Optimization (PSO) to adjust the weights of two Multi-Layer Perceptron (MLPs)for neutrosophic sets classification. During the training process of the MLP, the WOA is employed to exploreand determine the optimal set of weights. The PSO algorithm adjusts the weights to optimize the performanceof the MLP as fine-tuning. Additionally, in this approach, two separate MLP models are employed. One MLPis dedicated to predicting degrees of truth membership, while the other MLP focuses on predicting degrees offalse membership. The difference between these memberships quantifies uncertainty, indicating the degree ofindeterminacy in predictions. The experimental results indicate the superior performance of our model comparedto previous work when evaluated on the Davidson dataset.展开更多
In air traffic control communications (ATCC), misunderstandings between pilots and controllers could result in fatal aviation accidents. Fortunately, advanced automatic speech recognition technology has emerged as a p...In air traffic control communications (ATCC), misunderstandings between pilots and controllers could result in fatal aviation accidents. Fortunately, advanced automatic speech recognition technology has emerged as a promising means of preventing miscommunications and enhancing aviation safety. However, most existing speech recognition methods merely incorporate external language models on the decoder side, leading to insufficient semantic alignment between speech and text modalities during the encoding phase. Furthermore, it is challenging to model acoustic context dependencies over long distances due to the longer speech sequences than text, especially for the extended ATCC data. To address these issues, we propose a speech-text multimodal dual-tower architecture for speech recognition. It employs cross-modal interactions to achieve close semantic alignment during the encoding stage and strengthen its capabilities in modeling auditory long-distance context dependencies. In addition, a two-stage training strategy is elaborately devised to derive semantics-aware acoustic representations effectively. The first stage focuses on pre-training the speech-text multimodal encoding module to enhance inter-modal semantic alignment and aural long-distance context dependencies. The second stage fine-tunes the entire network to bridge the input modality variation gap between the training and inference phases and boost generalization performance. Extensive experiments demonstrate the effectiveness of the proposed speech-text multimodal speech recognition method on the ATCC and AISHELL-1 datasets. It reduces the character error rate to 6.54% and 8.73%, respectively, and exhibits substantial performance gains of 28.76% and 23.82% compared with the best baseline model. The case studies indicate that the obtained semantics-aware acoustic representations aid in accurately recognizing terms with similar pronunciations but distinctive semantics. The research provides a novel modeling paradigm for semantics-aware speech recognition in air traffic control communications, which could contribute to the advancement of intelligent and efficient aviation safety management.展开更多
Reporting is essential in language use,including the re-expression of other people’s or self’s words,opinions,psychological activities,etc.Grasping the translation methods of reported speech in German academic paper...Reporting is essential in language use,including the re-expression of other people’s or self’s words,opinions,psychological activities,etc.Grasping the translation methods of reported speech in German academic papers is very important to improve the accuracy of academic paper translation.This study takes the translation of“Internationalization of German Universities”(Die Internationalisierung der deutschen Hochschulen),an academic paper of higher education,as an example to explore the translation methods of reported speech in German academic papers.It is found that the use of word order conversion,part of speech conversion and split translation methods can make the translation more accurate and fluent.This paper helps to grasp the rules and characteristics of the translation of reported speech in German academic papers,and also provides a reference for improving the quality of German-Chinese translation.展开更多
In recent years,the usage of social networking sites has considerably increased in the Arab world.It has empowered individuals to express their opinions,especially in politics.Furthermore,various organizations that op...In recent years,the usage of social networking sites has considerably increased in the Arab world.It has empowered individuals to express their opinions,especially in politics.Furthermore,various organizations that operate in the Arab countries have embraced social media in their day-to-day business activities at different scales.This is attributed to business owners’understanding of social media’s importance for business development.However,the Arabic morphology is too complicated to understand due to the availability of nearly 10,000 roots and more than 900 patterns that act as the basis for verbs and nouns.Hate speech over online social networking sites turns out to be a worldwide issue that reduces the cohesion of civil societies.In this background,the current study develops a Chaotic Elephant Herd Optimization with Machine Learning for Hate Speech Detection(CEHOML-HSD)model in the context of the Arabic language.The presented CEHOML-HSD model majorly concentrates on identifying and categorising the Arabic text into hate speech and normal.To attain this,the CEHOML-HSD model follows different sub-processes as discussed herewith.At the initial stage,the CEHOML-HSD model undergoes data pre-processing with the help of the TF-IDF vectorizer.Secondly,the Support Vector Machine(SVM)model is utilized to detect and classify the hate speech texts made in the Arabic language.Lastly,the CEHO approach is employed for fine-tuning the parameters involved in SVM.This CEHO approach is developed by combining the chaotic functions with the classical EHO algorithm.The design of the CEHO algorithm for parameter tuning shows the novelty of the work.A widespread experimental analysis was executed to validate the enhanced performance of the proposed CEHOML-HSD approach.The comparative study outcomes established the supremacy of the proposed CEHOML-HSD model over other approaches.展开更多
The teaching of English speeches in universities aims to enhance oral communication ability,improve English communication skills,and expand English knowledge,occupying a core position in English teaching in universiti...The teaching of English speeches in universities aims to enhance oral communication ability,improve English communication skills,and expand English knowledge,occupying a core position in English teaching in universities.This article takes the theory of second language acquisition as the background,analyzes the important role and value of this theory in English speech teaching in universities,and explores how to apply the theory of second language acquisition in English speech teaching in universities.It aims to strengthen the cultivation of English skilled talents and provide a brief reference for improving English speech teaching in universities.展开更多
Speech emotion recognition(SER)uses acoustic analysis to find features for emotion recognition and examines variations in voice that are caused by emotions.The number of features acquired with acoustic analysis is ext...Speech emotion recognition(SER)uses acoustic analysis to find features for emotion recognition and examines variations in voice that are caused by emotions.The number of features acquired with acoustic analysis is extremely high,so we introduce a hybrid filter-wrapper feature selection algorithm based on an improved equilibrium optimizer for constructing an emotion recognition system.The proposed algorithm implements multi-objective emotion recognition with the minimum number of selected features and maximum accuracy.First,we use the information gain and Fisher Score to sort the features extracted from signals.Then,we employ a multi-objective ranking method to evaluate these features and assign different importance to them.Features with high rankings have a large probability of being selected.Finally,we propose a repair strategy to address the problem of duplicate solutions in multi-objective feature selection,which can improve the diversity of solutions and avoid falling into local traps.Using random forest and K-nearest neighbor classifiers,four English speech emotion datasets are employed to test the proposed algorithm(MBEO)as well as other multi-objective emotion identification techniques.The results illustrate that it performs well in inverted generational distance,hypervolume,Pareto solutions,and execution time,and MBEO is appropriate for high-dimensional English SER.展开更多
Machine Learning(ML)algorithms play a pivotal role in Speech Emotion Recognition(SER),although they encounter a formidable obstacle in accurately discerning a speaker’s emotional state.The examination of the emotiona...Machine Learning(ML)algorithms play a pivotal role in Speech Emotion Recognition(SER),although they encounter a formidable obstacle in accurately discerning a speaker’s emotional state.The examination of the emotional states of speakers holds significant importance in a range of real-time applications,including but not limited to virtual reality,human-robot interaction,emergency centers,and human behavior assessment.Accurately identifying emotions in the SER process relies on extracting relevant information from audio inputs.Previous studies on SER have predominantly utilized short-time characteristics such as Mel Frequency Cepstral Coefficients(MFCCs)due to their ability to capture the periodic nature of audio signals effectively.Although these traits may improve their ability to perceive and interpret emotional depictions appropriately,MFCCS has some limitations.So this study aims to tackle the aforementioned issue by systematically picking multiple audio cues,enhancing the classifier model’s efficacy in accurately discerning human emotions.The utilized dataset is taken from the EMO-DB database,preprocessing input speech is done using a 2D Convolution Neural Network(CNN)involves applying convolutional operations to spectrograms as they afford a visual representation of the way the audio signal frequency content changes over time.The next step is the spectrogram data normalization which is crucial for Neural Network(NN)training as it aids in faster convergence.Then the five auditory features MFCCs,Chroma,Mel-Spectrogram,Contrast,and Tonnetz are extracted from the spectrogram sequentially.The attitude of feature selection is to retain only dominant features by excluding the irrelevant ones.In this paper,the Sequential Forward Selection(SFS)and Sequential Backward Selection(SBS)techniques were employed for multiple audio cues features selection.Finally,the feature sets composed from the hybrid feature extraction methods are fed into the deep Bidirectional Long Short Term Memory(Bi-LSTM)network to discern emotions.Since the deep Bi-LSTM can hierarchically learn complex features and increases model capacity by achieving more robust temporal modeling,it is more effective than a shallow Bi-LSTM in capturing the intricate tones of emotional content existent in speech signals.The effectiveness and resilience of the proposed SER model were evaluated by experiments,comparing it to state-of-the-art SER techniques.The results indicated that the model achieved accuracy rates of 90.92%,93%,and 92%over the Ryerson Audio-Visual Database of Emotional Speech and Song(RAVDESS),Berlin Database of Emotional Speech(EMO-DB),and The Interactive Emotional Dyadic Motion Capture(IEMOCAP)datasets,respectively.These findings signify a prominent enhancement in the ability to emotional depictions identification in speech,showcasing the potential of the proposed model in advancing the SER field.展开更多
Arabic is the world’s first language,categorized by its rich and complicated grammatical formats.Furthermore,the Arabic morphology can be perplexing because nearly 10,000 roots and 900 patterns were the basis for ver...Arabic is the world’s first language,categorized by its rich and complicated grammatical formats.Furthermore,the Arabic morphology can be perplexing because nearly 10,000 roots and 900 patterns were the basis for verbs and nouns.The Arabic language consists of distinct variations utilized in a community and particular situations.Social media sites are a medium for expressing opinions and social phenomena like racism,hatred,offensive language,and all kinds of verbal violence.Such conduct does not impact particular nations,communities,or groups only,extending beyond such areas into people’s everyday lives.This study introduces an Improved Ant Lion Optimizer with Deep Learning Dirven Offensive and Hate Speech Detection(IALODL-OHSD)on Arabic Cross-Corpora.The presented IALODL-OHSD model mainly aims to detect and classify offensive/hate speech expressed on social media.In the IALODL-OHSD model,a threestage process is performed,namely pre-processing,word embedding,and classification.Primarily,data pre-processing is performed to transform the Arabic social media text into a useful format.In addition,the word2vec word embedding process is utilized to produce word embeddings.The attentionbased cascaded long short-term memory(ACLSTM)model is utilized for the classification process.Finally,the IALO algorithm is exploited as a hyperparameter optimizer to boost classifier results.To illustrate a brief result analysis of the IALODL-OHSD model,a detailed set of simulations were performed.The extensive comparison study portrayed the enhanced performance of the IALODL-OHSD model over other approaches.展开更多
In recent years,speech synthesis systems have allowed for the produc-tion of very high-quality voices.Therefore,research in this domain is now turning to the problem of integrating emotions into speech.However,the met...In recent years,speech synthesis systems have allowed for the produc-tion of very high-quality voices.Therefore,research in this domain is now turning to the problem of integrating emotions into speech.However,the method of con-structing a speech synthesizer for each emotion has some limitations.First,this method often requires an emotional-speech data set with many sentences.Such data sets are very time-intensive and labor-intensive to complete.Second,training each of these models requires computers with large computational capabilities and a lot of effort and time for model tuning.In addition,each model for each emotion failed to take advantage of data sets of other emotions.In this paper,we propose a new method to synthesize emotional speech in which the latent expressions of emotions are learned from a small data set of professional actors through a Flow-tron model.In addition,we provide a new method to build a speech corpus that is scalable and whose quality is easy to control.Next,to produce a high-quality speech synthesis model,we used this data set to train the Tacotron 2 model.We used it as a pre-trained model to train the Flowtron model.We applied this method to synthesize Vietnamese speech with sadness and happiness.Mean opi-nion score(MOS)assessment results show that MOS is 3.61 for sadness and 3.95 for happiness.In conclusion,the proposed method proves to be more effec-tive for a high degree of automation and fast emotional sentence generation,using a small emotional-speech data set.展开更多
Automatic Speech Emotion Recognition(SER)is used to recognize emotion from speech automatically.Speech Emotion recognition is working well in a laboratory environment but real-time emotion recognition has been influen...Automatic Speech Emotion Recognition(SER)is used to recognize emotion from speech automatically.Speech Emotion recognition is working well in a laboratory environment but real-time emotion recognition has been influenced by the variations in gender,age,the cultural and acoustical background of the speaker.The acoustical resemblance between emotional expressions further increases the complexity of recognition.Many recent research works are concentrated to address these effects individually.Instead of addressing every influencing attribute individually,we would like to design a system,which reduces the effect that arises on any factor.We propose a two-level Hierarchical classifier named Interpreter of responses(IR).Thefirst level of IR has been realized using Support Vector Machine(SVM)and Gaussian Mixer Model(GMM)classifiers.In the second level of IR,a discriminative SVM classifier has been trained and tested with meta information offirst-level classifiers along with the input acoustical feature vector which is used in primary classifiers.To train the system with a corpus of versatile nature,an integrated emotion corpus has been composed using emotion samples of 5 speech corpora,namely;EMO-DB,IITKGP-SESC,SAVEE Corpus,Spanish emotion corpus,CMU's Woogle corpus.The hierarchical classifier has been trained and tested using MFCC and Low-Level Descriptors(LLD).The empirical analysis shows that the proposed classifier outperforms the traditional classifiers.The proposed ensemble design is very generic and can be adapted even when the number and nature of features change.Thefirst-level classifiers GMM or SVM may be replaced with any other learning algorithm.展开更多
Speech disorders are a common type of childhood disease.Through experimental intervention,this study aims to improve the vocabulary comprehension levels and language ability of children with speech disorders through t...Speech disorders are a common type of childhood disease.Through experimental intervention,this study aims to improve the vocabulary comprehension levels and language ability of children with speech disorders through the language cognition and emotional speech community method.We also conduct a statistical analysis of the inter-ventional effect.Among children with speech disorders in Dongguan City,224 were selected and grouped accord-ing to their receptive language ability and IQ.The 112 children in the experimental group(EG)received speech therapy with language cognitive and emotional speech community,while the 112 children in the control group(CG)only received conventional treatment.After six months of experimental intervention,the Peabody Picture Vocabulary Test-Revised(PPVT-R)was used to test the language ability of the two groups.Overall,we employed a quantitative approach to obtain numerical values,examine the variables identified,and test hypotheses.Further-more,we used descriptive statistics to explore the research questions related to the study and statistically describe the overall distribution of the demographic variables.The statistical t-test was used to analyze the data.The data shows that after intervention through language cognition and emotional speech community therapy,the PPVT-R score of the EG was significantly higher than that of the CG.Therefore,we conclude that there is a significant difference in language ability between the EG and CG after the therapy.Although both groups improved,the post-therapy language level of EG is significantly higher than that of CG.The total effective rate in EG is higher than CG,and the difference is statistically significant(p<0.05).Therefore,we conclude that the language cogni-tion and emotional speech community method is effective as an interventional treatment of children’s speech dis-orders and that it is more effective than traditional treatment methods.展开更多
Speech recognition systems have become a unique human-computer interaction(HCI)family.Speech is one of the most naturally developed human abilities;speech signal processing opens up a transparent and hand-free computa...Speech recognition systems have become a unique human-computer interaction(HCI)family.Speech is one of the most naturally developed human abilities;speech signal processing opens up a transparent and hand-free computation experience.This paper aims to present a retrospective yet modern approach to the world of speech recognition systems.The development journey of ASR(Automatic Speech Recognition)has seen quite a few milestones and breakthrough technologies that have been highlighted in this paper.A step-by-step rundown of the fundamental stages in developing speech recognition systems has been presented,along with a brief discussion of various modern-day developments and applications in this domain.This review paper aims to summarize and provide a beginning point for those starting in the vast field of speech signal processing.Since speech recognition has a vast potential in various industries like telecommunication,emotion recognition,healthcare,etc.,this review would be helpful to researchers who aim at exploring more applications that society can quickly adopt in future years of evolution.展开更多
This study aims to address the deviation in downstream tasks caused by inaccurate recognition results when applying Automatic Speech Recognition(ASR)technology in the Air Traffic Control(ATC)field.This paper presents ...This study aims to address the deviation in downstream tasks caused by inaccurate recognition results when applying Automatic Speech Recognition(ASR)technology in the Air Traffic Control(ATC)field.This paper presents a novel cascaded model architecture,namely Conformer-CTC/Attention-T5(CCAT),to build a highly accurate and robust ATC speech recognition model.To tackle the challenges posed by noise and fast speech rate in ATC,the Conformer model is employed to extract robust and discriminative speech representations from raw waveforms.On the decoding side,the Attention mechanism is integrated to facilitate precise alignment between input features and output characters.The Text-To-Text Transfer Transformer(T5)language model is also introduced to handle particular pronunciations and code-mixing issues,providing more accurate and concise textual output for downstream tasks.To enhance the model’s robustness,transfer learning and data augmentation techniques are utilized in the training strategy.The model’s performance is optimized by performing hyperparameter tunings,such as adjusting the number of attention heads,encoder layers,and the weights of the loss function.The experimental results demonstrate the significant contributions of data augmentation,hyperparameter tuning,and error correction models to the overall model performance.On the Our ATC Corpus dataset,the proposed model achieves a Character Error Rate(CER)of 3.44%,representing a 3.64%improvement compared to the baseline model.Moreover,the effectiveness of the proposed model is validated on two publicly available datasets.On the AISHELL-1 dataset,the CCAT model achieves a CER of 3.42%,showcasing a 1.23%improvement over the baseline model.Similarly,on the LibriSpeech dataset,the CCAT model achieves a Word Error Rate(WER)of 5.27%,demonstrating a performance improvement of 7.67%compared to the baseline model.Additionally,this paper proposes an evaluation criterion for assessing the robustness of ATC speech recognition systems.In robustness evaluation experiments based on this criterion,the proposed model demonstrates a performance improvement of 22%compared to the baseline model.展开更多
Applied linguistics is one of the fields in the linguistics domain and deals with the practical applications of the language studies such as speech processing,language teaching,translation and speech therapy.The ever-...Applied linguistics is one of the fields in the linguistics domain and deals with the practical applications of the language studies such as speech processing,language teaching,translation and speech therapy.The ever-growing Online Social Networks(OSNs)experience a vital issue to confront,i.e.,hate speech.Amongst the OSN-oriented security problems,the usage of offensive language is the most important threat that is prevalently found across the Internet.Based on the group targeted,the offensive language varies in terms of adult content,hate speech,racism,cyberbullying,abuse,trolling and profanity.Amongst these,hate speech is the most intimidating form of using offensive language in which the targeted groups or individuals are intimidated with the intent of creating harm,social chaos or violence.Machine Learning(ML)techniques have recently been applied to recognize hate speech-related content.The current research article introduces a Grasshopper Optimization with an Attentive Recurrent Network for Offensive Speech Detection(GOARN-OSD)model for social media.The GOARNOSD technique integrates the concepts of DL and metaheuristic algorithms for detecting hate speech.In the presented GOARN-OSD technique,the primary stage involves the data pre-processing and word embedding processes.Then,this study utilizes the Attentive Recurrent Network(ARN)model for hate speech recognition and classification.At last,the Grasshopper Optimization Algorithm(GOA)is exploited as a hyperparameter optimizer to boost the performance of the hate speech recognition process.To depict the promising performance of the proposed GOARN-OSD method,a widespread experimental analysis was conducted.The comparison study outcomes demonstrate the superior performance of the proposed GOARN-OSD model over other state-of-the-art approaches.展开更多
Automatic speech recognition(ASR)systems have emerged as indispensable tools across a wide spectrum of applications,ranging from transcription services to voice-activated assistants.To enhance the performance of these...Automatic speech recognition(ASR)systems have emerged as indispensable tools across a wide spectrum of applications,ranging from transcription services to voice-activated assistants.To enhance the performance of these systems,it is important to deploy efficient models capable of adapting to diverse deployment conditions.In recent years,on-demand pruning methods have obtained significant attention within the ASR domain due to their adaptability in various deployment scenarios.However,these methods often confront substantial trade-offs,particularly in terms of unstable accuracy when reducing the model size.To address challenges,this study introduces two crucial empirical findings.Firstly,it proposes the incorporation of an online distillation mechanism during on-demand pruning training,which holds the promise of maintaining more consistent accuracy levels.Secondly,it proposes the utilization of the Mogrifier long short-term memory(LSTM)language model(LM),an advanced iteration of the conventional LSTM LM,as an effective alternative for pruning targets within the ASR framework.Through rigorous experimentation on the ASR system,employing the Mogrifier LSTM LM and training it using the suggested joint on-demand pruning and online distillation method,this study provides compelling evidence.The results exhibit that the proposed methods significantly outperform a benchmark model trained solely with on-demand pruning methods.Impressively,the proposed strategic configuration successfully reduces the parameter count by approximately 39%,all the while minimizing trade-offs.展开更多
The hidden danger of the automatic speaker verification(ASV)system is various spoofed speeches.These threats can be classified into two categories,namely logical access(LA)and physical access(PA).To improve identifica...The hidden danger of the automatic speaker verification(ASV)system is various spoofed speeches.These threats can be classified into two categories,namely logical access(LA)and physical access(PA).To improve identification capability of spoofed speech detection,this paper considers the research on features.Firstly,following the idea of modifying the constant-Q-based features,this work considered adding variance or mean to the constant-Q-based cepstral domain to obtain good performance.Secondly,linear frequency cepstral coefficients(LFCCs)performed comparably with constant-Q-based features.Finally,we proposed linear frequency variance-based cepstral coefficients(LVCCs)and linear frequency mean-based cepstral coefficients(LMCCs)for identification of speech spoofing.LVCCs and LMCCs could be attained by adding the frame variance or the mean to the log magnitude spectrum based on LFCC features.The proposed novel features were evaluated on ASVspoof 2019 datase.The experimental results show that compared with known hand-crafted features,LVCCs and LMCCs are more effective in resisting spoofed speech attack.展开更多
Existing speech retrieval systems are frequently confronted with expanding volumes of speech data.The dynamic updating strategy applied to construct the index can timely process to add or remove unnecessary speech dat...Existing speech retrieval systems are frequently confronted with expanding volumes of speech data.The dynamic updating strategy applied to construct the index can timely process to add or remove unnecessary speech data to meet users’real-time retrieval requirements.This study proposes an efficient method for retrieving encryption speech,using unsupervised deep hashing and B+ tree dynamic index,which avoid privacy leak-age of speech data and enhance the accuracy and efficiency of retrieval.The cloud’s encryption speech library is constructed by using the multi-threaded Dijk-Gentry-Halevi-Vaikuntanathan(DGHV)Fully Homomorphic Encryption(FHE)technique,which encrypts the original speech.In addition,this research employs Residual Neural Network18-Gated Recurrent Unit(ResNet18-GRU),which is used to learn the compact binary hash codes,store binary hash codes in the designed B+tree index table,and create a mapping relation of one to one between the binary hash codes and the corresponding encrypted speech.External B+tree index technology is applied to achieve dynamic index updating of the B+tree index table,thereby satisfying users’needs for real-time retrieval.The experimental results on THCHS-30 and TIMIT showed that the retrieval accuracy of the proposed method is more than 95.84%compared to the existing unsupervised hashing methods.The retrieval efficiency is greatly improved.Compared to the method of using hash index tables,and the speech data’s security is effectively guaranteed.展开更多
In recent years,the CET-6(College English Test,Band 6)has become an important standard to measure the English language ability of Chinese college students,and listening is a challenging task for many students.The appl...In recent years,the CET-6(College English Test,Band 6)has become an important standard to measure the English language ability of Chinese college students,and listening is a challenging task for many students.The application of indirect speech act theory in CET-6 listening is seldom studied.Therefore,it is crucial to study on it.Based on the two observation points of indirect speech act theory in CET-6 listening,this study analyzes the specific embodiment of conventional indirect speech acts and non-conventional indirect speech acts in listening,and discusses the effective teaching methods of CET-6 listening.展开更多
文摘The objective was to measure the effect of various face masks on speech recognition threshold and the word recognition score in the presence of varying background noise levels.20 normal-hearing adult subjects(a total of 40 ears)participated.Pure tone audiometry followed by speech recognition threshold and word recognition score at the most comfortable level in varying signal-to-noise ratios(SNR0,SNR10,and SNR15)using surgical,pleated cloth,and N95 masks.Using surgical,cloth,and N95 masks,speech recognition thresholds increased by 1.8 dB,4.4 dB,and 5.05 dB,respectively.Word recognition scores decreased by 32%without a mask,43.7%in a surgical mask,46.3%in a cloth mask,and 46.7%in N95 mask conditions,between SNR15 and SNR0.The speech recognition threshold was negatively affected with cloth and N95 masks.Surgical masks do not affect the word recognition scores at lower background noise levels.However,as the signal-to-noise ratio decreased,even the surgical,cloth,and N95 masks significantly impacted the word recognition score even in normal-hearing individuals.
基金This work is part of the research projects LaTe4PoliticES(PID2022-138099OBI00)funded by MICIU/AEI/10.13039/501100011033the European Regional Development Fund(ERDF)-A Way of Making Europe and LT-SWM(TED2021-131167B-I00)funded by MICIU/AEI/10.13039/501100011033the European Union NextGenerationEU/PRTR.Mr.Ronghao Pan is supported by the Programa Investigo grant,funded by the Region of Murcia,the Spanish Ministry of Labour and Social Economy and the European Union-NextGenerationEU under the“Plan de Recuperación,Transformación y Resiliencia(PRTR).”。
文摘Large Language Models(LLMs)are increasingly demonstrating their ability to understand natural language and solve complex tasks,especially through text generation.One of the relevant capabilities is contextual learning,which involves the ability to receive instructions in natural language or task demonstrations to generate expected outputs for test instances without the need for additional training or gradient updates.In recent years,the popularity of social networking has provided a medium through which some users can engage in offensive and harmful online behavior.In this study,we investigate the ability of different LLMs,ranging from zero-shot and few-shot learning to fine-tuning.Our experiments show that LLMs can identify sexist and hateful online texts using zero-shot and few-shot approaches through information retrieval.Furthermore,it is found that the encoder-decoder model called Zephyr achieves the best results with the fine-tuning approach,scoring 86.811%on the Explainable Detection of Online Sexism(EDOS)test-set and 57.453%on the Multilingual Detection of Hate Speech Against Immigrants and Women in Twitter(HatEval)test-set.Finally,it is confirmed that the evaluated models perform well in hate text detection,as they beat the best result in the HatEval task leaderboard.The error analysis shows that contextual learning had difficulty distinguishing between types of hate speech and figurative language.However,the fine-tuned approach tends to produce many false positives.
文摘Detecting hate speech automatically in social media forensics has emerged as a highly challenging task due tothe complex nature of language used in such platforms. Currently, several methods exist for classifying hatespeech, but they still suffer from ambiguity when differentiating between hateful and offensive content and theyalso lack accuracy. The work suggested in this paper uses a combination of the Whale Optimization Algorithm(WOA) and Particle Swarm Optimization (PSO) to adjust the weights of two Multi-Layer Perceptron (MLPs)for neutrosophic sets classification. During the training process of the MLP, the WOA is employed to exploreand determine the optimal set of weights. The PSO algorithm adjusts the weights to optimize the performanceof the MLP as fine-tuning. Additionally, in this approach, two separate MLP models are employed. One MLPis dedicated to predicting degrees of truth membership, while the other MLP focuses on predicting degrees offalse membership. The difference between these memberships quantifies uncertainty, indicating the degree ofindeterminacy in predictions. The experimental results indicate the superior performance of our model comparedto previous work when evaluated on the Davidson dataset.
基金This research was funded by Shenzhen Science and Technology Program(Grant No.RCBS20221008093121051)the General Higher Education Project of Guangdong Provincial Education Department(Grant No.2020ZDZX3085)+1 种基金China Postdoctoral Science Foundation(Grant No.2021M703371)the Post-Doctoral Foundation Project of Shenzhen Polytechnic(Grant No.6021330002K).
文摘In air traffic control communications (ATCC), misunderstandings between pilots and controllers could result in fatal aviation accidents. Fortunately, advanced automatic speech recognition technology has emerged as a promising means of preventing miscommunications and enhancing aviation safety. However, most existing speech recognition methods merely incorporate external language models on the decoder side, leading to insufficient semantic alignment between speech and text modalities during the encoding phase. Furthermore, it is challenging to model acoustic context dependencies over long distances due to the longer speech sequences than text, especially for the extended ATCC data. To address these issues, we propose a speech-text multimodal dual-tower architecture for speech recognition. It employs cross-modal interactions to achieve close semantic alignment during the encoding stage and strengthen its capabilities in modeling auditory long-distance context dependencies. In addition, a two-stage training strategy is elaborately devised to derive semantics-aware acoustic representations effectively. The first stage focuses on pre-training the speech-text multimodal encoding module to enhance inter-modal semantic alignment and aural long-distance context dependencies. The second stage fine-tunes the entire network to bridge the input modality variation gap between the training and inference phases and boost generalization performance. Extensive experiments demonstrate the effectiveness of the proposed speech-text multimodal speech recognition method on the ATCC and AISHELL-1 datasets. It reduces the character error rate to 6.54% and 8.73%, respectively, and exhibits substantial performance gains of 28.76% and 23.82% compared with the best baseline model. The case studies indicate that the obtained semantics-aware acoustic representations aid in accurately recognizing terms with similar pronunciations but distinctive semantics. The research provides a novel modeling paradigm for semantics-aware speech recognition in air traffic control communications, which could contribute to the advancement of intelligent and efficient aviation safety management.
文摘Reporting is essential in language use,including the re-expression of other people’s or self’s words,opinions,psychological activities,etc.Grasping the translation methods of reported speech in German academic papers is very important to improve the accuracy of academic paper translation.This study takes the translation of“Internationalization of German Universities”(Die Internationalisierung der deutschen Hochschulen),an academic paper of higher education,as an example to explore the translation methods of reported speech in German academic papers.It is found that the use of word order conversion,part of speech conversion and split translation methods can make the translation more accurate and fluent.This paper helps to grasp the rules and characteristics of the translation of reported speech in German academic papers,and also provides a reference for improving the quality of German-Chinese translation.
基金Princess Nourah bint Abdulrahman University Researchers Supporting Project Number(PNURSP2024R263)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.This study is supported via funding from Prince Sattam bin Abdulaziz University Project Number(PSAU/2024/R/1445).
文摘In recent years,the usage of social networking sites has considerably increased in the Arab world.It has empowered individuals to express their opinions,especially in politics.Furthermore,various organizations that operate in the Arab countries have embraced social media in their day-to-day business activities at different scales.This is attributed to business owners’understanding of social media’s importance for business development.However,the Arabic morphology is too complicated to understand due to the availability of nearly 10,000 roots and more than 900 patterns that act as the basis for verbs and nouns.Hate speech over online social networking sites turns out to be a worldwide issue that reduces the cohesion of civil societies.In this background,the current study develops a Chaotic Elephant Herd Optimization with Machine Learning for Hate Speech Detection(CEHOML-HSD)model in the context of the Arabic language.The presented CEHOML-HSD model majorly concentrates on identifying and categorising the Arabic text into hate speech and normal.To attain this,the CEHOML-HSD model follows different sub-processes as discussed herewith.At the initial stage,the CEHOML-HSD model undergoes data pre-processing with the help of the TF-IDF vectorizer.Secondly,the Support Vector Machine(SVM)model is utilized to detect and classify the hate speech texts made in the Arabic language.Lastly,the CEHO approach is employed for fine-tuning the parameters involved in SVM.This CEHO approach is developed by combining the chaotic functions with the classical EHO algorithm.The design of the CEHO algorithm for parameter tuning shows the novelty of the work.A widespread experimental analysis was executed to validate the enhanced performance of the proposed CEHOML-HSD approach.The comparative study outcomes established the supremacy of the proposed CEHOML-HSD model over other approaches.
文摘The teaching of English speeches in universities aims to enhance oral communication ability,improve English communication skills,and expand English knowledge,occupying a core position in English teaching in universities.This article takes the theory of second language acquisition as the background,analyzes the important role and value of this theory in English speech teaching in universities,and explores how to apply the theory of second language acquisition in English speech teaching in universities.It aims to strengthen the cultivation of English skilled talents and provide a brief reference for improving English speech teaching in universities.
文摘Speech emotion recognition(SER)uses acoustic analysis to find features for emotion recognition and examines variations in voice that are caused by emotions.The number of features acquired with acoustic analysis is extremely high,so we introduce a hybrid filter-wrapper feature selection algorithm based on an improved equilibrium optimizer for constructing an emotion recognition system.The proposed algorithm implements multi-objective emotion recognition with the minimum number of selected features and maximum accuracy.First,we use the information gain and Fisher Score to sort the features extracted from signals.Then,we employ a multi-objective ranking method to evaluate these features and assign different importance to them.Features with high rankings have a large probability of being selected.Finally,we propose a repair strategy to address the problem of duplicate solutions in multi-objective feature selection,which can improve the diversity of solutions and avoid falling into local traps.Using random forest and K-nearest neighbor classifiers,four English speech emotion datasets are employed to test the proposed algorithm(MBEO)as well as other multi-objective emotion identification techniques.The results illustrate that it performs well in inverted generational distance,hypervolume,Pareto solutions,and execution time,and MBEO is appropriate for high-dimensional English SER.
文摘Machine Learning(ML)algorithms play a pivotal role in Speech Emotion Recognition(SER),although they encounter a formidable obstacle in accurately discerning a speaker’s emotional state.The examination of the emotional states of speakers holds significant importance in a range of real-time applications,including but not limited to virtual reality,human-robot interaction,emergency centers,and human behavior assessment.Accurately identifying emotions in the SER process relies on extracting relevant information from audio inputs.Previous studies on SER have predominantly utilized short-time characteristics such as Mel Frequency Cepstral Coefficients(MFCCs)due to their ability to capture the periodic nature of audio signals effectively.Although these traits may improve their ability to perceive and interpret emotional depictions appropriately,MFCCS has some limitations.So this study aims to tackle the aforementioned issue by systematically picking multiple audio cues,enhancing the classifier model’s efficacy in accurately discerning human emotions.The utilized dataset is taken from the EMO-DB database,preprocessing input speech is done using a 2D Convolution Neural Network(CNN)involves applying convolutional operations to spectrograms as they afford a visual representation of the way the audio signal frequency content changes over time.The next step is the spectrogram data normalization which is crucial for Neural Network(NN)training as it aids in faster convergence.Then the five auditory features MFCCs,Chroma,Mel-Spectrogram,Contrast,and Tonnetz are extracted from the spectrogram sequentially.The attitude of feature selection is to retain only dominant features by excluding the irrelevant ones.In this paper,the Sequential Forward Selection(SFS)and Sequential Backward Selection(SBS)techniques were employed for multiple audio cues features selection.Finally,the feature sets composed from the hybrid feature extraction methods are fed into the deep Bidirectional Long Short Term Memory(Bi-LSTM)network to discern emotions.Since the deep Bi-LSTM can hierarchically learn complex features and increases model capacity by achieving more robust temporal modeling,it is more effective than a shallow Bi-LSTM in capturing the intricate tones of emotional content existent in speech signals.The effectiveness and resilience of the proposed SER model were evaluated by experiments,comparing it to state-of-the-art SER techniques.The results indicated that the model achieved accuracy rates of 90.92%,93%,and 92%over the Ryerson Audio-Visual Database of Emotional Speech and Song(RAVDESS),Berlin Database of Emotional Speech(EMO-DB),and The Interactive Emotional Dyadic Motion Capture(IEMOCAP)datasets,respectively.These findings signify a prominent enhancement in the ability to emotional depictions identification in speech,showcasing the potential of the proposed model in advancing the SER field.
基金Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2022R263)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.The authors would like to thank the Deanship of Scientific Research at Umm Al-Qura University for supporting this work by Grant Code:22UQU4340237DSR43.
文摘Arabic is the world’s first language,categorized by its rich and complicated grammatical formats.Furthermore,the Arabic morphology can be perplexing because nearly 10,000 roots and 900 patterns were the basis for verbs and nouns.The Arabic language consists of distinct variations utilized in a community and particular situations.Social media sites are a medium for expressing opinions and social phenomena like racism,hatred,offensive language,and all kinds of verbal violence.Such conduct does not impact particular nations,communities,or groups only,extending beyond such areas into people’s everyday lives.This study introduces an Improved Ant Lion Optimizer with Deep Learning Dirven Offensive and Hate Speech Detection(IALODL-OHSD)on Arabic Cross-Corpora.The presented IALODL-OHSD model mainly aims to detect and classify offensive/hate speech expressed on social media.In the IALODL-OHSD model,a threestage process is performed,namely pre-processing,word embedding,and classification.Primarily,data pre-processing is performed to transform the Arabic social media text into a useful format.In addition,the word2vec word embedding process is utilized to produce word embeddings.The attentionbased cascaded long short-term memory(ACLSTM)model is utilized for the classification process.Finally,the IALO algorithm is exploited as a hyperparameter optimizer to boost classifier results.To illustrate a brief result analysis of the IALODL-OHSD model,a detailed set of simulations were performed.The extensive comparison study portrayed the enhanced performance of the IALODL-OHSD model over other approaches.
基金funded by the Hanoi University of Science and Technology(HUST)under grant number T2018-PC-210.
文摘In recent years,speech synthesis systems have allowed for the produc-tion of very high-quality voices.Therefore,research in this domain is now turning to the problem of integrating emotions into speech.However,the method of con-structing a speech synthesizer for each emotion has some limitations.First,this method often requires an emotional-speech data set with many sentences.Such data sets are very time-intensive and labor-intensive to complete.Second,training each of these models requires computers with large computational capabilities and a lot of effort and time for model tuning.In addition,each model for each emotion failed to take advantage of data sets of other emotions.In this paper,we propose a new method to synthesize emotional speech in which the latent expressions of emotions are learned from a small data set of professional actors through a Flow-tron model.In addition,we provide a new method to build a speech corpus that is scalable and whose quality is easy to control.Next,to produce a high-quality speech synthesis model,we used this data set to train the Tacotron 2 model.We used it as a pre-trained model to train the Flowtron model.We applied this method to synthesize Vietnamese speech with sadness and happiness.Mean opi-nion score(MOS)assessment results show that MOS is 3.61 for sadness and 3.95 for happiness.In conclusion,the proposed method proves to be more effec-tive for a high degree of automation and fast emotional sentence generation,using a small emotional-speech data set.
文摘Automatic Speech Emotion Recognition(SER)is used to recognize emotion from speech automatically.Speech Emotion recognition is working well in a laboratory environment but real-time emotion recognition has been influenced by the variations in gender,age,the cultural and acoustical background of the speaker.The acoustical resemblance between emotional expressions further increases the complexity of recognition.Many recent research works are concentrated to address these effects individually.Instead of addressing every influencing attribute individually,we would like to design a system,which reduces the effect that arises on any factor.We propose a two-level Hierarchical classifier named Interpreter of responses(IR).Thefirst level of IR has been realized using Support Vector Machine(SVM)and Gaussian Mixer Model(GMM)classifiers.In the second level of IR,a discriminative SVM classifier has been trained and tested with meta information offirst-level classifiers along with the input acoustical feature vector which is used in primary classifiers.To train the system with a corpus of versatile nature,an integrated emotion corpus has been composed using emotion samples of 5 speech corpora,namely;EMO-DB,IITKGP-SESC,SAVEE Corpus,Spanish emotion corpus,CMU's Woogle corpus.The hierarchical classifier has been trained and tested using MFCC and Low-Level Descriptors(LLD).The empirical analysis shows that the proposed classifier outperforms the traditional classifiers.The proposed ensemble design is very generic and can be adapted even when the number and nature of features change.Thefirst-level classifiers GMM or SVM may be replaced with any other learning algorithm.
文摘Speech disorders are a common type of childhood disease.Through experimental intervention,this study aims to improve the vocabulary comprehension levels and language ability of children with speech disorders through the language cognition and emotional speech community method.We also conduct a statistical analysis of the inter-ventional effect.Among children with speech disorders in Dongguan City,224 were selected and grouped accord-ing to their receptive language ability and IQ.The 112 children in the experimental group(EG)received speech therapy with language cognitive and emotional speech community,while the 112 children in the control group(CG)only received conventional treatment.After six months of experimental intervention,the Peabody Picture Vocabulary Test-Revised(PPVT-R)was used to test the language ability of the two groups.Overall,we employed a quantitative approach to obtain numerical values,examine the variables identified,and test hypotheses.Further-more,we used descriptive statistics to explore the research questions related to the study and statistically describe the overall distribution of the demographic variables.The statistical t-test was used to analyze the data.The data shows that after intervention through language cognition and emotional speech community therapy,the PPVT-R score of the EG was significantly higher than that of the CG.Therefore,we conclude that there is a significant difference in language ability between the EG and CG after the therapy.Although both groups improved,the post-therapy language level of EG is significantly higher than that of CG.The total effective rate in EG is higher than CG,and the difference is statistically significant(p<0.05).Therefore,we conclude that the language cogni-tion and emotional speech community method is effective as an interventional treatment of children’s speech dis-orders and that it is more effective than traditional treatment methods.
文摘Speech recognition systems have become a unique human-computer interaction(HCI)family.Speech is one of the most naturally developed human abilities;speech signal processing opens up a transparent and hand-free computation experience.This paper aims to present a retrospective yet modern approach to the world of speech recognition systems.The development journey of ASR(Automatic Speech Recognition)has seen quite a few milestones and breakthrough technologies that have been highlighted in this paper.A step-by-step rundown of the fundamental stages in developing speech recognition systems has been presented,along with a brief discussion of various modern-day developments and applications in this domain.This review paper aims to summarize and provide a beginning point for those starting in the vast field of speech signal processing.Since speech recognition has a vast potential in various industries like telecommunication,emotion recognition,healthcare,etc.,this review would be helpful to researchers who aim at exploring more applications that society can quickly adopt in future years of evolution.
基金This study was co-supported by the National Key R&D Program of China(No.2021YFF0603904)National Natural Science Foundation of China(U1733203)Safety Capacity Building Project of Civil Aviation Administration of China(TM2019-16-1/3).
文摘This study aims to address the deviation in downstream tasks caused by inaccurate recognition results when applying Automatic Speech Recognition(ASR)technology in the Air Traffic Control(ATC)field.This paper presents a novel cascaded model architecture,namely Conformer-CTC/Attention-T5(CCAT),to build a highly accurate and robust ATC speech recognition model.To tackle the challenges posed by noise and fast speech rate in ATC,the Conformer model is employed to extract robust and discriminative speech representations from raw waveforms.On the decoding side,the Attention mechanism is integrated to facilitate precise alignment between input features and output characters.The Text-To-Text Transfer Transformer(T5)language model is also introduced to handle particular pronunciations and code-mixing issues,providing more accurate and concise textual output for downstream tasks.To enhance the model’s robustness,transfer learning and data augmentation techniques are utilized in the training strategy.The model’s performance is optimized by performing hyperparameter tunings,such as adjusting the number of attention heads,encoder layers,and the weights of the loss function.The experimental results demonstrate the significant contributions of data augmentation,hyperparameter tuning,and error correction models to the overall model performance.On the Our ATC Corpus dataset,the proposed model achieves a Character Error Rate(CER)of 3.44%,representing a 3.64%improvement compared to the baseline model.Moreover,the effectiveness of the proposed model is validated on two publicly available datasets.On the AISHELL-1 dataset,the CCAT model achieves a CER of 3.42%,showcasing a 1.23%improvement over the baseline model.Similarly,on the LibriSpeech dataset,the CCAT model achieves a Word Error Rate(WER)of 5.27%,demonstrating a performance improvement of 7.67%compared to the baseline model.Additionally,this paper proposes an evaluation criterion for assessing the robustness of ATC speech recognition systems.In robustness evaluation experiments based on this criterion,the proposed model demonstrates a performance improvement of 22%compared to the baseline model.
基金Princess Nourah bint Abdulrahman University Researchers Supporting Project number (PNURSP2023R281)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia+1 种基金Deanship of Scientific Research at Umm Al-Qura University for supporting this work by Grant Code: (22UQU4331004DSR031)supported via funding from Prince Sattam bin Abdulaziz University project number (PSAU/2023/R/1444).
文摘Applied linguistics is one of the fields in the linguistics domain and deals with the practical applications of the language studies such as speech processing,language teaching,translation and speech therapy.The ever-growing Online Social Networks(OSNs)experience a vital issue to confront,i.e.,hate speech.Amongst the OSN-oriented security problems,the usage of offensive language is the most important threat that is prevalently found across the Internet.Based on the group targeted,the offensive language varies in terms of adult content,hate speech,racism,cyberbullying,abuse,trolling and profanity.Amongst these,hate speech is the most intimidating form of using offensive language in which the targeted groups or individuals are intimidated with the intent of creating harm,social chaos or violence.Machine Learning(ML)techniques have recently been applied to recognize hate speech-related content.The current research article introduces a Grasshopper Optimization with an Attentive Recurrent Network for Offensive Speech Detection(GOARN-OSD)model for social media.The GOARNOSD technique integrates the concepts of DL and metaheuristic algorithms for detecting hate speech.In the presented GOARN-OSD technique,the primary stage involves the data pre-processing and word embedding processes.Then,this study utilizes the Attentive Recurrent Network(ARN)model for hate speech recognition and classification.At last,the Grasshopper Optimization Algorithm(GOA)is exploited as a hyperparameter optimizer to boost the performance of the hate speech recognition process.To depict the promising performance of the proposed GOARN-OSD method,a widespread experimental analysis was conducted.The comparison study outcomes demonstrate the superior performance of the proposed GOARN-OSD model over other state-of-the-art approaches.
基金supported by Institute of Information&communications Technology Planning&Evaluation(IITP)grant funded by the Korea government(MSIT)(No.2022-0-00377,Development of Intelligent Analysis and Classification Based Contents Class Categorization Technique to Prevent Imprudent Harmful Media Distribution).
文摘Automatic speech recognition(ASR)systems have emerged as indispensable tools across a wide spectrum of applications,ranging from transcription services to voice-activated assistants.To enhance the performance of these systems,it is important to deploy efficient models capable of adapting to diverse deployment conditions.In recent years,on-demand pruning methods have obtained significant attention within the ASR domain due to their adaptability in various deployment scenarios.However,these methods often confront substantial trade-offs,particularly in terms of unstable accuracy when reducing the model size.To address challenges,this study introduces two crucial empirical findings.Firstly,it proposes the incorporation of an online distillation mechanism during on-demand pruning training,which holds the promise of maintaining more consistent accuracy levels.Secondly,it proposes the utilization of the Mogrifier long short-term memory(LSTM)language model(LM),an advanced iteration of the conventional LSTM LM,as an effective alternative for pruning targets within the ASR framework.Through rigorous experimentation on the ASR system,employing the Mogrifier LSTM LM and training it using the suggested joint on-demand pruning and online distillation method,this study provides compelling evidence.The results exhibit that the proposed methods significantly outperform a benchmark model trained solely with on-demand pruning methods.Impressively,the proposed strategic configuration successfully reduces the parameter count by approximately 39%,all the while minimizing trade-offs.
基金National Natural Science Foundation of China(No.62001100)。
文摘The hidden danger of the automatic speaker verification(ASV)system is various spoofed speeches.These threats can be classified into two categories,namely logical access(LA)and physical access(PA).To improve identification capability of spoofed speech detection,this paper considers the research on features.Firstly,following the idea of modifying the constant-Q-based features,this work considered adding variance or mean to the constant-Q-based cepstral domain to obtain good performance.Secondly,linear frequency cepstral coefficients(LFCCs)performed comparably with constant-Q-based features.Finally,we proposed linear frequency variance-based cepstral coefficients(LVCCs)and linear frequency mean-based cepstral coefficients(LMCCs)for identification of speech spoofing.LVCCs and LMCCs could be attained by adding the frame variance or the mean to the log magnitude spectrum based on LFCC features.The proposed novel features were evaluated on ASVspoof 2019 datase.The experimental results show that compared with known hand-crafted features,LVCCs and LMCCs are more effective in resisting spoofed speech attack.
基金supported by the NationalNatural Science Foundation of China(No.61862041).
文摘Existing speech retrieval systems are frequently confronted with expanding volumes of speech data.The dynamic updating strategy applied to construct the index can timely process to add or remove unnecessary speech data to meet users’real-time retrieval requirements.This study proposes an efficient method for retrieving encryption speech,using unsupervised deep hashing and B+ tree dynamic index,which avoid privacy leak-age of speech data and enhance the accuracy and efficiency of retrieval.The cloud’s encryption speech library is constructed by using the multi-threaded Dijk-Gentry-Halevi-Vaikuntanathan(DGHV)Fully Homomorphic Encryption(FHE)technique,which encrypts the original speech.In addition,this research employs Residual Neural Network18-Gated Recurrent Unit(ResNet18-GRU),which is used to learn the compact binary hash codes,store binary hash codes in the designed B+tree index table,and create a mapping relation of one to one between the binary hash codes and the corresponding encrypted speech.External B+tree index technology is applied to achieve dynamic index updating of the B+tree index table,thereby satisfying users’needs for real-time retrieval.The experimental results on THCHS-30 and TIMIT showed that the retrieval accuracy of the proposed method is more than 95.84%compared to the existing unsupervised hashing methods.The retrieval efficiency is greatly improved.Compared to the method of using hash index tables,and the speech data’s security is effectively guaranteed.
文摘In recent years,the CET-6(College English Test,Band 6)has become an important standard to measure the English language ability of Chinese college students,and listening is a challenging task for many students.The application of indirect speech act theory in CET-6 listening is seldom studied.Therefore,it is crucial to study on it.Based on the two observation points of indirect speech act theory in CET-6 listening,this study analyzes the specific embodiment of conventional indirect speech acts and non-conventional indirect speech acts in listening,and discusses the effective teaching methods of CET-6 listening.
