A connectionist approach to continuous speech recognition

Michael A. Franzini, Michael J. Witbrock, Kai-Fu 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.<
BibTeX
@inproceedings{franzini2003connectionist,
  author = {Michael A. Franzini and Michael J. Witbrock and Kai-Fu 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