Soft decoding of temporal derivatives for robust distributed speech recognition in packet loss

@article{James2005SoftDO,
  title={Soft decoding of temporal derivatives for robust distributed speech recognition in packet loss},
  author={Alastair Bruce James and Ben P. Milner},
  journal={Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.},
  year={2005},
  volume={1},
  pages={I/345-I/348 Vol. 1}
}
The aim of this work is to improve distributed speech recognition accuracy in packet loss by considering the effect of loss on the temporal derivatives of the feature vector. Analysis of temporal derivatives reveals they suffer severe distortion when static vectors are lost in times of packet loss. The application of missing feature theory and soft-decoding techniques are considered for compensating against packet loss at the decoding stage of recognition. An extension to these methods is… CONTINUE READING

References

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

A Comparison of Packet Loss Compensation Methods and Interleaving for Speech Recognition in Burst-Like Packet Loss

  • A. B. James, A. Gomez, B. P. Milner
  • Proc. ICSLP,
  • 2004
Highly Influential
3 Excerpts

A.Vizinho, “Robust Automatic Speech Recognition with Missing and Unreliable Acoustic Data

  • M. Cooke, P.Green, L. Josifovski
  • Speech Communication,
  • 2001
2 Excerpts

L.Josifovski, M.Cooke, P.Green, “Soft Decisions in Missing Data Techniques for Robust Automatic Speech Recognition

  • J. Barker
  • Proc ICSLP
  • 2000
2 Excerpts

Applebaum, "Robust speakerindependent word features using static, dynamic and acceleration features

  • T.H.B.A. Hanson
  • Proc. ICASSP,
  • 1990
1 Excerpt

Similar Papers

Loading similar papers…