Neural-network-based HMM adaptation for noisy speech

@inproceedings{Furui2001NeuralnetworkbasedHA,
  title={Neural-network-based HMM adaptation for noisy speech},
  author={Sadaoki Furui and Daisuke Itoh},
  booktitle={ICASSP},
  year={2001}
}
This paper proposes a new method, using neural networks, of adapting phone HMMs to noisy speech. The neural networks are designed to map clean speech HMMs to noise-adapted HMMs, using noise HMMs and signal-to-noise ratios (SNRs) as inputs, and are trained to minimize the mean square error between the output HMMs and the target noise-adapted HMMs. In evaluation, the proposed method was used to recognize noisy broadcast-news speech in speaker-dependent and -independent modes. The trained networks… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.

References

Publications referenced by this paper.
Showing 1-7 of 7 references

Furui : “ A maximum likelihood procedure for a universal adaptation method based on HMM composition ”

S.
Proc . ICASSP • 1995

An improved approach to the hidden Markov model decomposition of speech and noise ”

M. J. F. Gales, S. J. Young
Proc . ICASSP • 1992

Young: “An improved approach to the hidden Markov model decomposition of speech and noise

S.J.M.J.F. Gales
Proc. ICASSP, • 1992
View 1 Excerpt

Similar Papers

Loading similar papers…