期刊文献+
共找到7篇文章
< 1 >
每页显示 20 50 100
一种基于声音分类学习的神经模型研究 被引量:2
1
作者 王莉莉 张少白 《计算机技术与发展》 2011年第12期127-130,共4页
语音感知能力是人类感知系统的一个重要方面。在婴儿时期,随着婴儿对母语音位的不断接触和学习,会产生分类感知和知觉磁效应现象,这与自组织特征映射的经典表述相矛盾。文中提出了一种能对这种现象进行解释的神经模型,并通过模型的仿真... 语音感知能力是人类感知系统的一个重要方面。在婴儿时期,随着婴儿对母语音位的不断接触和学习,会产生分类感知和知觉磁效应现象,这与自组织特征映射的经典表述相矛盾。文中提出了一种能对这种现象进行解释的神经模型,并通过模型的仿真实验证明了该模型的可行性和正确性。模型进一步预测磁效应的产生是因为原型元音比非原型元音有更小的听觉皮层表示,通过功能磁共振成像实验对模型提出的预测进行了论证。 展开更多
关键词 声音分类学习 知觉磁效应 自组织特征映射
下载PDF
基于深度学习声音识别技术的老年听障人群无障碍交互产品设计策略研究
2
作者 江雪莹 邵斌 《艺术科技》 2024年第16期154-156,共3页
目的:随着我国老龄化程度的加深,老龄化人群听觉功能障碍成为不可忽视的社会议题。听力损失不仅损害老年人的感知能力,更会对其身心健康和社会参与造成严重影响。文章以老年听障人群为研究对象,探究以深度学习声音识别技术促进老年听障... 目的:随着我国老龄化程度的加深,老龄化人群听觉功能障碍成为不可忽视的社会议题。听力损失不仅损害老年人的感知能力,更会对其身心健康和社会参与造成严重影响。文章以老年听障人群为研究对象,探究以深度学习声音识别技术促进老年听障人群无障碍交互的可行性,探究无障碍交互产品设计策略。方法:基于无障碍设计理论、老年听障人群特征,研究深度学习声音识别技术在辅听软件中的作用。通过声音识别和音频分类技术,实现对语言信息和关键环境声(如门铃声、警报声、婴儿哭声等)的监测、判断与提醒,帮助听障用户通过感官代偿的方式在日常生活中及时获取声音的重要信息。结果:文章归纳了基于深度学习声音识别技术的无障碍交互产品设计策略,并讨论实现过程中面临的技术难点,提出优化建议。围绕感官代偿、简化操作、安全隐私及情感化界面,设计适合老年听障用户的交互界面和多模态提醒方式,改善老年听障人群的听力状态,帮助他们更好地生活。结论:深度学习声音识别技术为无障碍交互产品设计提供了新的可能,使手机辅听软件可以切实为老年听障人群这一特殊群体提供帮助,进而推动社会包容与人文关怀设计的发展。 展开更多
关键词 深度学习声音识别技术 老年听障人群 无障碍交互产品 交互设计 辅听软件
下载PDF
FOXP2与语言相关性研究 被引量:1
3
作者 李慧 《生理科学进展》 CAS CSCD 北大核心 2013年第6期453-457,共5页
人类言语以及某些鸟类、蝙蝠和海洋哺乳动物的交流系统是听觉指导下的、习得性发声运动行为,对其潜在的神经和遗传机制研究将揭示其异同。FOXP2是第一例鉴定的语言相关基因。本文综述了动物模型感觉指导下的运动学习中,FOXP2和它调控的... 人类言语以及某些鸟类、蝙蝠和海洋哺乳动物的交流系统是听觉指导下的、习得性发声运动行为,对其潜在的神经和遗传机制研究将揭示其异同。FOXP2是第一例鉴定的语言相关基因。本文综述了动物模型感觉指导下的运动学习中,FOXP2和它调控的基因网络如何塑造皮层-基底神经节回路的神经可塑性,这将有助于我们理解语言这一复杂的认知表型。 展开更多
关键词 声音学习 FOXP2 基底神经节
下载PDF
Novel Active Learning Method for Speech Recognition 被引量:1
4
作者 Liu Gang Chen Wei Guo Jun 《China Communications》 SCIE CSCD 2010年第5期29-39,共11页
In speech recognition, acoustic modeling always requires tremendous transcribed samples, and the transcription becomes intensively time-consuming and costly. In order to aid this labor-intensive process, Active Learni... In speech recognition, acoustic modeling always requires tremendous transcribed samples, and the transcription becomes intensively time-consuming and costly. In order to aid this labor-intensive process, Active Learning (AL) is adopted for speech recognition, where only the most informative training samples are selected for manual annotation. In this paper, we propose a novel active learning method for Chinese acoustic modeling, the methods for initial training set selection based on Kullback-Leibler Divergence (KLD) and sample evaluation based on multi-level confusion networks are proposed and adopted in our active learning system, respectively. Our experiments show that our proposed method can achieve satisfying performances. 展开更多
关键词 active learning acoustic model speech recognition KLD confusion network
下载PDF
声纹识别技术在皮带撕裂检测中的应用
5
作者 李岩 《中文科技期刊数据库(全文版)工程技术》 2021年第2期350-351,共2页
本文针对皮带出现裂纹或被物体划伤,导致整条皮带撕裂损坏问题,以及作业环境复杂,现场人员巡检不及时等问题,分析了皮带机撕裂发生的原因;阐述了声纹识别技术以及深度学习技术在皮带撕裂检测系统的应用的必要性和可行性。
关键词 皮带撕裂 声音分离 高通滤波 声纹识别 声音深度学习
下载PDF
Phonological Metaphors in Stylistics Analysis
6
作者 CHEN Yali LUO Yuanyuan 《International English Education Research》 2018年第3期107-109,共3页
Stylistics is the study of style. It is a branch of linguistics concerned with the study of characteristic choices in use of language, made by different individuals or social groups in different situations of use. Acc... Stylistics is the study of style. It is a branch of linguistics concerned with the study of characteristic choices in use of language, made by different individuals or social groups in different situations of use. According to Martin (1991), grammatical metaphor is the process by which the meanings are multiply-coded at the level of grammar. Meaning variation represented by lexicogrammatical changes are metaphor, and meaning differences represented by sound system may also bring about metaphorical phenomenon. This paper seeks to explore the stylistic value of intonation metaphor in functional stylistics by analyzing the distribution of intonation metaphors in both public speeches and news reports. 展开更多
关键词 intonation metaphor STYLISTICS news reports public speech
下载PDF
Learn a rich foreign language research on teaching voice Chinese language of minority
7
作者 Kaiyan Wan 《International Journal of Technology Management》 2014年第2期26-28,共3页
Foreign teaching and Chinese language teaching of minority are two different forms of teaching in nature, both the nature and the system of teaching are different, but in the teaching objectives, content, principles, ... Foreign teaching and Chinese language teaching of minority are two different forms of teaching in nature, both the nature and the system of teaching are different, but in the teaching objectives, content, principles, methods, and therefore there are many similarities, so two studies outcomes can learn from each other. In this paper, with voice teaching as an example, we will talk about foreign language studies in ethnic minority Chinese Teaching. I think, in the teaching program design, the teaching Chinese minorities can learn from the simplified idea of teaching phonological Mr. Zhao Jin ruing, which is proposed foreign teaching Chinese, to simplify Voice teaching. In teaching principles, we should emphasize specific principles, instructional design based on students' different characteristics. In the teaching content, teaching should not only pay attention phonetic syllables within the system, but also more emphasis on syllables voice level teaching, especially teaching speech flow. In teaching methods, we should learn teaching, research tone, softly and so on. 展开更多
关键词 foreign language teaching the teaching of ethnic minorities voice teaching.
下载PDF
上一页 1 下一页 到第
使用帮助 返回顶部