Sixth International Conference on Spoken Language Processing
(ICSLP 2000)

Beijing, China
October 16-20, 2000

HMM Adaptation Using Vector Taylor Series for Noisy Speech Recognition

Alex Acero, Li Deng, Trausti Kristjansson, Jerry Zhang

Speech Technology Group, Microsoft Research, Redmond, WA, USA

In this paper we address the problem of robustness of speech recognition systems in noisy environments. The goal is to estimate the parameters of a HMM that is matched to a noisy environment, given a HMM trained with clean speech and knowledge of the acoustical environment. We propose a method based on truncated vector Taylor series that approximates the performance of a system trained with that corrupted speech. We also provide insight on the approximations used in the model of the environment and compare them with the lognormal approximation in PMC.

Full Paper

Bibliographic reference.  Acero, Alex / Deng, Li / Kristjansson, Trausti / Zhang, Jerry (2000): "HMM adaptation using vector taylor series for noisy speech recognition", In ICSLP-2000, vol.3, 869-872.