Influence of Different Speech Representations and HMM Training Strategies on ASR Performance
DOI:
https://doi.org/10.14311/896Keywords:
PLP, MFCC, Lombard effect, CLSD’05Abstract
This work studies the influence of various speech signal representations and speaking styles on the performance of automatic speech recognition (ASR). The efficiency of two approaches to hidden Markov model (HMM) training are compared.Common MFCC and PLP features were exposed to two sources of disturbance applied to the original wide-band speech: (i) stress (Lombard effect) and (ii) transfer channel distortion (simulated telephone line). Subsequently, the efficiencies of the two training strategies were evaluated. Finally, a study of the optimal number of training iterations is introduced.Downloads
Download data is not yet available.
Downloads
Published
2006-01-06
How to Cite
Bořil, H., & Fousek, P. (2006). Influence of Different Speech Representations and HMM Training Strategies on ASR Performance. Acta Polytechnica, 46(6). https://doi.org/10.14311/896
Issue
Section
Articles