On the use of residual cepstrum in speech recognition

Author

He, Jialong ; Liu, Li ; Palm, Günther

Author_Institution

Ulm Univ., Germany

Volume

1

fYear

1996

fDate

7-10 May 1996

Firstpage

5

Abstract

In speech recognition based on LPC analysis the prediction residues are usually ignored, only the LPC-derived cepstral coefficients (LPCC) are used to compose feature vectors. In this study, a number of parameters (called the residual cepstrum or RCEP) were calculated from these residues and their effectiveness for speech recognition was evaluated. It was shown that the RCEP do contain useful information, in particular, they are complementary to the LPCC. In an evaluation experiment, if the LPCC were used jointly with a few RCEP coefficients, the recognition rate of the English E-set letters was improved from 54% to 67% and from 69% to 71% by the use of HMMs based recognizer and the DTW based recognizer, respectively. In addition, Mel-scaled FFT based cepstrum (MFCC) was found to be superior to LPCC

Keywords

cepstral analysis; fast Fourier transforms; hidden Markov models; linear predictive coding; natural languages; speech coding; speech processing; speech recognition; DTW based recognizer; English E-set letters; HMM based recognizer; LPC analysis; LPC derived cepstral coefficients; MFCC; Mel-scaled FFT based cepstrum; RCEP coefficients; evaluation experiment; feature vector; prediction residues; recognition rate; residual cepstrum; Cepstral analysis; Cepstrum; Helium; Hidden Markov models; Linear predictive coding; Mel frequency cepstral coefficient; Parameter estimation; Poles and zeros; Speech analysis; Speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1996. ICASSP-96. Conference Proceedings., 1996 IEEE International Conference on

Conference_Location

Atlanta, GA

ISSN

1520-6149

Print_ISBN

0-7803-3192-3

Type

conf

DOI

10.1109/ICASSP.1996.540276

Filename

540276