A Maximum Likelihood Approach to Unsupervised Online Adaptation of Stochastic Vector Mapping Function for Robust Speech Recognition

• Published in: 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07 Vol. 4; pp. IV-773 - IV-776
• Main Authors: Donglai Zhu, Qiang Huo
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.04.2007
• Subjects: Automatic speech recognition; feature compensation; hidden Markov model; Hidden Markov models; maximum likelihood; Maximum likelihood estimation; online adaptation; robust speech recognition; Robustness; Speech recognition; Stochastic processes; Support vector machine classification; Support vector machines; Testing; Training data
• ISBN: 9781424407279; 1424407273
• ISSN: 1520-6149; 2379-190X
• DOI: 10.1109/ICASSP.2007.367027

In the past several years, we've been studying feature transformation approaches for robust automatic speech recognition (ASR) based on the concept of stochastic vector mapping (SVM) to compensating for possible "distortions" caused by factors irrelevant to phonetic classification in both training and recognition stages. Although we have demonstrated the usefulness of the SVM-based approaches for several robust ASR applications where diversified yet representative training data are available, the performance improvement of SVM-based approaches is less significant when there is a severe mismatch between training and testing conditions. In this paper, we present a maximum likelihood approach to unsupervised online adaptation (OLA) of SVM function parameters on an utterance-by-utterance basis for achieving further performance improvement. Its effectiveness is confirmed by evaluation experiments on Finnish AuroraS database.