We propose a new Bayesian approach to cope with a class of difficult robust speech recognition problems for those applications which only involve a couple of utterances, but every utterance involves a distinct yet complicated "distortion channel" from the intended message a speaker wants to convey to the received signal of a speech recognizer. It works by composing on-the-fly a testing-condition dependent prior distribution of HMM parameters for each testing utterance from a set of prior distributions elicited off-line from a rich set of training data. Encouraging results are obtained by applying this new method to a task of speaker independent continuous Mandarin speech recognition for speakers with different degree of accents.
Cite as: Huo, Q., Ma, B. (2000) Robust speech recognition based on off-line elicitation of multiple priors and on-line adaptive prior fusion. Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000), vol. 4, 480-483, doi: 10.21437/ICSLP.2000-853
@inproceedings{huo00_icslp,
author={Qiang Huo and Bin Ma},
title={{Robust speech recognition based on off-line elicitation of multiple priors and on-line adaptive prior fusion}},
year=2000,
booktitle={Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000)},
pages={vol. 4, 480-483},
doi={10.21437/ICSLP.2000-853}
}