ISCA Archive ICSLP 1994
ISCA Archive ICSLP 1994

Nonlinear time alignment in stochastic trajectory models for speech recognition

Mohamed Afify, Yifan Gong, Jean-Paul Haton

A nonlinear time alignment technique is presented in the framework of stochastic trajectory models (STM). We show how to obtain maximum likelihood (ML) estimates of model parameters, and how to use the technique during recognition with a slight additional computational overhead. Experimental results for a French 850 word continuous speech task are given. For a 10 speaker population, we test with various degrees of nonlinearity, and the introduced technique provides a slight improvement (about 1%) in the average word recognition rate.


Cite as: Afify, M., Gong, Y., Haton, J.-P. (1994) Nonlinear time alignment in stochastic trajectory models for speech recognition. Proc. 3rd International Conference on Spoken Language Processing (ICSLP 1994), 291-294

@inproceedings{afify94_icslp,
  author={Mohamed Afify and Yifan Gong and Jean-Paul Haton},
  title={{Nonlinear time alignment in stochastic trajectory models for speech recognition}},
  year=1994,
  booktitle={Proc. 3rd International Conference on Spoken Language Processing (ICSLP 1994)},
  pages={291--294}
}