This paper proposes a new method, using neural networks, of adapting phone HMMs to noise added speech. The network is designed to map clean speech HMMs to noise-adapted HMMs using inputs of clean speech phone HMMs, noise HMMs and signal-to-noise ratios (S/N). The network is trained to minimize the mean squared error between the output HMMs and the target noise-adapted HMMs. Noisy broadcast-news speech was recognized in speaker-dependent and speaker-independent network training conditions, and the trained networks were confirmed to be effective in the recognition of new speakers and under new noise and S/N conditions.
Cite as: Furui, S., Itoh, D. (2000) Noise adaptation of HMMs using neural networks. Proc. ASR2000 - Automatic Speech Recognition: Challenges for the New Millenium, 160-167
@inproceedings{furui00_asr, author={Sadaoki Furui and Daisuke Itoh}, title={{Noise adaptation of HMMs using neural networks}}, year=2000, booktitle={Proc. ASR2000 - Automatic Speech Recognition: Challenges for the New Millenium}, pages={160--167} }