Improving speech recognition performance via phone-dependent VQ codebooks and adaptive language models in SPHINX-II

M. Hwamg, Roni Rosenfeld, E. Theyer, R. Mosur, Lin Chase, R. Weide, Xuedong Huang, F. Alleva

Abstract

This paper presents improvements in acoustic and language modeling for automatic speech recognition. Specifically, semi-continuous HMMs (SCHMMs) with phone-dependent VQ codebooks are presented and incorporated into the SPHINX-II speech recognition system. The phone-dependent VQ codebooks relax the density-tying constraint in SCHMMs in order to obtain more detailed models. A 6% error rate reduction was achieved on the speaker-independent 20000-word Wall Street Journal (WSJ) task. Dynamic adaptation of the language model in the context of long documents is also explored. A maximum entropy framework is used to exploit long distance trigrams and trigger effects. A 10%-15% word error rate reduction is reported on the same WSJ task using the adaptive language modeling technique.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>
BibTeX
@inproceedings{hwamg1994improving,
  author = {M. Hwamg and Roni Rosenfeld and E. Theyer and R. Mosur and Lin Chase and R. Weide and Xuedong Huang and F. Alleva},
  title = {{Improving speech recognition performance via phone-dependent VQ codebooks and adaptive language models in SPHINX-II}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {1994},
  doi = {10.1109/icassp.1994.389235},
}

Loading related content...

Figure