British English and American English are regarded as the two major varieties of English in the world, and Canadian English is often treated as a variation of American English. The paper aims to identify the major phon...British English and American English are regarded as the two major varieties of English in the world, and Canadian English is often treated as a variation of American English. The paper aims to identify the major phonetic features of Canadian English by addressing its differences from British and American English based on a historical, demographical, and regional and dialectal analysis. Canadian English is a cultural phenomenon that has evolved on the basis of British English and under the heavy influence of American English. As a distinctive variety of English, Canadian English possesses its phonetic uniqueness. And in the context of globalization, Canadian English will remain subject to Americanization.展开更多
The inclusion of more potentially correct words in the candidate sets is important to improve the accuracy of Large Vocabulary Continuous Speech Recognition （LVCSR）. A candidate expansion algorithm based on the Weig...The inclusion of more potentially correct words in the candidate sets is important to improve the accuracy of Large Vocabulary Continuous Speech Recognition （LVCSR）. A candidate expansion algorithm based on the Weighted Syllable Confusion Matrix （WSCM） is proposed. First, WSCM is derived from a confusion network. Then, the reeognised candidates in the confusion network is used to conjeeture the most likely correct words based on WSCM, after which, the conjectured words are combined with the recognised candidates to produce an expanded candidate set. Finally, a combined model having mutual information and a trigram language model is used to rerank the candidates. The experiments on Mandarin film data show that an improvement of 9.57% in the character correction rate is obtained over the initial recognition performance on those light erroneous utterances.展开更多
Two fast and robust digital watermarking schemes for compressed music format and MIDI format are put forward, which are suitable for on-line distribution through the Internet. For compressed music, the watermark is em...Two fast and robust digital watermarking schemes for compressed music format and MIDI format are put forward, which are suitable for on-line distribution through the Internet. For compressed music, the watermark is embedded in partially uncompressed domain and the embedding scheme is closely related to music content. For MIDI, the watermark is embedded in virtual notes that are generated and randomly hide among the MIDI notes. This paper also presents a method for controlling usage and protecting against copying of digital music contents and their associated players. The digital music contents and their players installed in one computer cannot be used if they are copied to another computer. Even in the same computer, the duplicated digital music contents are not usable. The usage associated to the music content will restrict the running time and times. Also the music can be played and it will be automatically updated after each playing. The digital music cannot be accessible if its permitted usage expires.展开更多
文摘British English and American English are regarded as the two major varieties of English in the world, and Canadian English is often treated as a variation of American English. The paper aims to identify the major phonetic features of Canadian English by addressing its differences from British and American English based on a historical, demographical, and regional and dialectal analysis. Canadian English is a cultural phenomenon that has evolved on the basis of British English and under the heavy influence of American English. As a distinctive variety of English, Canadian English possesses its phonetic uniqueness. And in the context of globalization, Canadian English will remain subject to Americanization.
基金supported by the National Natural Science Foundation of China under Grants No.61005004,No.61175011,No.61171193the Next-Generation Broadband Wireless Mobile Communications Network Technology Key Project under Grant No.2011ZX03002-005-01+2 种基金the One Church,One Family,One Purpose(111Project)under Grant No.B08004the Key Project of Ministry of Science and Technology of China under Grant No.2012ZX-03002019-002the National High Techni-cal Research and Development Program of China(863Program)under Grant No.2011A-A01A205
文摘The inclusion of more potentially correct words in the candidate sets is important to improve the accuracy of Large Vocabulary Continuous Speech Recognition （LVCSR）. A candidate expansion algorithm based on the Weighted Syllable Confusion Matrix （WSCM） is proposed. First, WSCM is derived from a confusion network. Then, the reeognised candidates in the confusion network is used to conjeeture the most likely correct words based on WSCM, after which, the conjectured words are combined with the recognised candidates to produce an expanded candidate set. Finally, a combined model having mutual information and a trigram language model is used to rerank the candidates. The experiments on Mandarin film data show that an improvement of 9.57% in the character correction rate is obtained over the initial recognition performance on those light erroneous utterances.
文摘Two fast and robust digital watermarking schemes for compressed music format and MIDI format are put forward, which are suitable for on-line distribution through the Internet. For compressed music, the watermark is embedded in partially uncompressed domain and the embedding scheme is closely related to music content. For MIDI, the watermark is embedded in virtual notes that are generated and randomly hide among the MIDI notes. This paper also presents a method for controlling usage and protecting against copying of digital music contents and their associated players. The digital music contents and their players installed in one computer cannot be used if they are copied to another computer. Even in the same computer, the duplicated digital music contents are not usable. The usage associated to the music content will restrict the running time and times. Also the music can be played and it will be automatically updated after each playing. The digital music cannot be accessible if its permitted usage expires.
