HMM-based speech recognition using state-dependent, discriminatively derived transforms on mel-warped DFT features

@article{Chengalvarayan1997HMMbasedSR,
  title={HMM-based speech recognition using state-dependent, discriminatively derived transforms on mel-warped DFT features},
  author={Rathinavelu Chengalvarayan and Li Deng},
  journal={IEEE Trans. Speech and Audio Processing},
  year={1997},
  volume={5},
  pages={243-256}
}
In the study reported in this paper, we investigate interactions of front-end feature extraction and back-end classification techniques in hidden Markov model-based (HMMbased) speech recognition. The proposed model focuses on dimensionality reduction of the mel-warped discrete fourier transform (DFT) feature space subject to maximal preservation of speech classification information, and aims at finding an optimal linear transformation on the mel-warped DFT according to the minimum… CONTINUE READING
Highly Cited
This paper has 84 citations. REVIEW CITATIONS
51 Citations
26 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 51 extracted citations

84 Citations

0510'97'02'08'14
Citations per Year
Semantic Scholar estimates that this publication has 84 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 26 references

A comparison of signal processing front ends for automatic word recognition

  • C. R. Jankowski, H. Vo, R. P. Lippman
  • IEEE Trans. Speech Audio Processing, vol. 3, pp…
  • 1995
1 Excerpt

An integrated ANN-HMM speech recognition system based on minimum classification error training

  • M. Rahim, C. H. Lee, B. H. Juang
  • Proc. 1995 IEEE Workshop on Automatic Speech…
  • 1995

Use of generalized dynamic feature parameters for speech recognition: Maximum likelihood and minimum classification error approaches

  • Proc. ICASSP, 1995, pp. 373–376.
  • 1995
3 Excerpts

Similar Papers

Loading similar papers…