Title :
On the use of normalized LPC error towards better large vocabulary speech recognition systems
Author :
Chengalvarayan, Rathinavelu
Author_Institution :
Lucent Technol., AT&T Bell Labs., Naperville, IL, USA
Abstract :
Linear prediction (LP) analysis is widely used in speech recognition for representing the short time spectral envelope information of speech. The predictive residues are usually ignored in LP analysis based speech recognition system. In this study, the normalized residual error based on LP is introduced and the performance of the recognizer has been further improved by the addition of this new feature along with its first and second order derivative parameters. The convergence property of the training procedure based on the minimum classification error (MCE) approach is investigated, and experimental results on the city name recognition task demonstrated a 8% string error rate reduction by using the extended feature set as compared to conventional feature set
Keywords :
cepstral analysis; coding errors; convergence of numerical methods; error statistics; linear predictive coding; pattern classification; signal representation; speech coding; speech recognition; HMM; cepstral coefficients; city name recognition task; continuous density mixtures; convergence property; experimental results; extended feature set; first order derivative parameters; hidden Markov model; large vocabulary speech recognition systems; linear prediction analysis; minimum classification error; normalized LPC error; normalized residual error; performance; predictive residues; second order derivative parameters; short time spectral envelope; speaker independent continuous speech recognition; speech discrimination; speech representation; string error rate reduction; training procedure; Autocorrelation; Cepstral analysis; Cepstrum; Computer errors; Hidden Markov models; Linear predictive coding; Speech analysis; Speech processing; Speech recognition; Vocabulary;
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.1998.674356