Title :
Automatic speech recognition based on cepstral coefficients and a mel-based discrete energy operator
Author :
Tolba, Hesham ; O´Shaughnessy, Douglas
Author_Institution :
INRS Telecommun., Ile des Soeurs, Que., Canada
Abstract :
In this paper, a novel feature vector based on both mel frequency cepstral coefficients (MFCCs) and a mel-based nonlinear discrete-time energy operator (MDEO) is proposed to be used as the input of an HMM-based automatic continuous speech recognition (ACSR) system. Our goal is to improve the performance of such a recognizer using the new feature vector. Experiments show that the use of the new feature vector increases the recognition rate of the ACSR system. The HTK hidden Markov model toolkit was used throughout. Experiments were done on both the TIMIT and NTIMIT databases. For the TIMIT database, when the MDEO was included in the feature vector to test a multi-speaker ACSR system, we found that the error rate decreased by about 9.51%. On the other hand, for NTIMIT, the MDEO deteriorates the performance of the recognizer. That is, the new feature vector is useful for clean speech but not for telephone speech
Keywords :
cepstral analysis; discrete time systems; error statistics; hidden Markov models; mathematical operators; speech recognition; ACSR; HMM-based automatic continuous speech recognition; HTK hidden Markov model toolkit; MDEO; MFCCs; NTIMIT database; TIMIT database; automatic speech recognition; cepstral coefficients; clean speech; error rate; feature vector; mel frequency cepstral coefficients; mel-based nonlinear discrete-time energy operator; multi-speaker ACSR system; performance; recognition rate; telephone speech; Amplitude modulation; Automatic speech recognition; Business; Cepstral analysis; Energy measurement; Frequency estimation; Frequency modulation; Hidden Markov models; Resonance; Spatial databases;
Conference_Titel :
Acoustics, Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-4428-6
DOI :
10.1109/ICASSP.1998.675429