A connectionist approach to continuous speech recognition

M. Franzini, Michael Witbrock, K.-f. Lee

Abstract

The authors have applied connectionist learning procedures to speaker-independent continuous recognition, creating a system which has achieved 97% word accuracy and 91% sentence accuracy in preliminary tests on the TI/NBS connected-digits database. The system uses a four-layer back-propagation network with recurrent connections to generate and refine hypotheses about the identity of an utterance over successive intervals. The hypotheses generated by the network are used as input to a Markov-chain-based Viterbi recognizer which produces a final identification of the entire utterance.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>
BibTeX
@inproceedings{franzini2003connectionist,
  author = {M. Franzini and Michael Witbrock and K.-F. Lee},
  title = {{A connectionist approach to continuous speech recognition}},
  booktitle = {International Conference on Acoustics, Speech, and Signal Processing},
  year = {2003},
  doi = {10.1109/icassp.1989.266456},
}

Loading related content...

Figure