DocumentCode :
319596
Title :
Effect of different sampling rates and feature vector sizes on speech recognition performance
Author :
Ssnderson, C. ; Paliwal, Kuldip K.
Author_Institution :
Sch. of Microelectron. Eng., Griffith Univ., Brisbane, Qld., Australia
Volume :
1
fYear :
1997
fDate :
4-4 Dec. 1997
Firstpage :
161
Abstract :
We conduct a systematic study to evaluate the effect of the sampling rate and feature vector size on the performance of a hidden Markov model (HMM) based speech recognizer. We investigate the use of the following two types of features: linear prediction (LP) derived cepstral coefficients (LPCC) and Mel frequency cepstral coefficients (MFCC). We demonstrate that for the LPCC front-end, the optimum sampling rate and feature vector size are 12 kHz and 14, respectively. We also show that for different sampling rates, the accuracy peaks at different sizes of the feature vector. For the MFCC front-end, the optimum feature vector size and sampling rate are 14 and 14 kHz, respectively.
Keywords :
cepstral analysis; hidden Markov models; prediction theory; signal sampling; speech recognition; 12 kHz; 14 kHz; HMM; Mel frequency cepstral coefficients; feature vector size; hidden Markov model; linear prediction cepstral coefficients; sampling rates; speech recognition performance; Australia; Cepstral analysis; Databases; Hidden Markov models; Mel frequency cepstral coefficient; Microelectronics; Sampling methods; Speech analysis; Speech recognition; Testing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
TENCON '97. IEEE Region 10 Annual Conference. Speech and Image Technologies for Computing and Telecommunications., Proceedings of IEEE
Conference_Location :
Brisbane, Qld., Australia
Print_ISBN :
0-7803-4365-4
Type :
conf
DOI :
10.1109/TENCON.1997.647282
Filename :
647282
Link To Document :
بازگشت