Bi-mel-scale frequency cepstrum and its application in telephone speech recognition

查看全文 作　　者：CHEN Jingdong;XU Bo;HUANG Taiyi(National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences Beijing 100080)

出　　处：《Chinese Journal of Acoustics》索引1998年第17卷第3期,共10页

摘　　要：A new kind of feature for speech recognition, called Bi-Mel-scale Frequency Cepstrum (BMFC) is proposed. To calculate the BMFC, the speech signal is first segmented into short intervals and the bispectrum of each segment is estimated; then the bispectrum is smoothed by two-dimensional mel-scale inverse filter bank; finally, the bi-mel-scale frequency cepstrum coefficients are obtained by decorrelating the outputs of the filter bank with twodimensional Discrete Cosine Transform (DCT). Preliminary experiments show that the new feature can improve the performance of a telephone speech recognizer and is more robust to white noise than the conventional LPCC (Linear Prediction Coefficients) and MFCC (Mel-scale Frequency Cepstrum Coefficents) used in speech 关键词：LPCC IEEE BMFC

相关文献

参考文献（11）
引证文献（0）
耦合文献（1）

参考文献(11)

耦合文献(1)

互联网出版许可证新出网证(渝)字10号全国400电话 - 免长途话费

Bi-mel-scale frequency cepstrum and its application in telephone speech recognition

参考文献(11)

耦合文献(1)

用户提示