ISCA Archive ICSLP 2000
ISCA Archive ICSLP 2000

HMM adaptation using vector taylor series for noisy speech recognition

Alex Acero, Li Deng, Trausti Kristjansson, Jerry Zhang

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.


Cite as: Acero, A., Deng, L., Kristjansson, T., Zhang, J. (2000) HMM adaptation using vector taylor series for noisy speech recognition. Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000), vol. 3, 869-872

@inproceedings{acero00_icslp,
  author={Alex Acero and Li Deng and Trausti Kristjansson and Jerry Zhang},
  title={{HMM adaptation using vector taylor series for noisy speech recognition}},
  year=2000,
  booktitle={Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000)},
  pages={vol. 3, 869-872}
}