| A new frequency scale of Chinese whispered speech in the application of speaker identification |
| |
| 作者姓名： | LIN Wei YANG Lili XU Boling |
| |
| 作者单位： | Institute of Acoustics & Key Laboratory of Modern Acoustics, Nanjing University, Nanjing 210093, China |
| |
| 摘 要： | In this paper, the frequency characteristics of Chinese whispered speech were investigated by a filter bank analysis. It was shown that the first and the third formants were more important than the other formants in the speaker identification of Chinese whispered speech. The experiment showed that the 800?1200 Hz and 2800?3200 Hz ranges were the most significant frequency ranges in discriminating the speaker. Based on this result, a new feature scale named whisper sensitive scale (WSS) was proposed to replace the common scale, Mel scale, and to extract the cepstral coefficient from whispered speech signal. Furthermore, a speaker identification system in whispered speech was presented based on the modified Hidden Markov Models integrating advantages of WSCC (the whisper sensitive cepstral coefficient) and LPCC. And the new system performed better in solving the problem of speaker identification of Chinese whispered speech than the traditional method.
|
| 关 键 词： | speaker identification Chinese whispered speech whisper sensitive scale |
A new frequency scale of Chinese whispered speech in the application of speaker identification |
| |
| LIN Wei,YANG Lili,XU Boling.A new frequency scale of Chinese whispered speech in the application of speaker identification[J].Progress in Natural Science,2006,16(10):1072-1078. |
| |
| Authors: | LIN Wei YANG Lili XU Boling |
| |
| Institution: | Institute of Acoustics & Key Laboratory of Modern Acoustics,Nanjing University,Nanjing 210093,China |
| |
| Abstract: | In this paper, the frequency characteristics of Chinese whispered speech were investigated by a filter bank analysis. It was shown that the first and the third formants were more important than the other formants in the speaker identification of Chinese whispered speech. The experiment showed that the 800?1200 Hz and 2800?3200 Hz ranges were the most significant frequency ranges in discriminating the speaker. Based on this result, a new feature scale named whisper sensitive scale (WSS) was proposed to replace the common scale, Mel scale, and to extract the cepstral coefficient from whispered speech signal. Furthermore, a speaker identification system in whispered speech was presented based on the modified Hidden Markov Models integrating advantages of WSCC (the whisper sensitive cepstral coefficient) and LPCC. And the new system performed better in solving the problem of speaker identification of Chinese whispered speech than the traditional method. |
| |
| Keywords: | speaker identification Chinese whispered speech whisper sensitive scale |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《自然科学进展(英文版)》浏览原始摘要信息 |
| 点击此处可从《自然科学进展(英文版)》下载免费的PDF全文 |
