Phonotactic and Lexical Constraints in Speech Recognition

Abstract

We demonstrate a method for partitioning a large lexicon into small equivalence classes, based on sequential phonetic and prosodic constraints. The representation is attractive for speech recognition systems because it allows all but a small number of word candidates to be excluded, using only gross phonetic and prosodic information. The approach is a robust one in that the representation is relatively insensitive to phonetic variability and recognition error.

Cite

Text

Huttenlocher and Sue. "Phonotactic and Lexical Constraints in Speech Recognition." AAAI Conference on Artificial Intelligence, 1983.

Markdown

[Huttenlocher and Sue. "Phonotactic and Lexical Constraints in Speech Recognition." AAAI Conference on Artificial Intelligence, 1983.](https://mlanthology.org/aaai/1983/huttenlocher1983aaai-phonotactic/)

BibTeX

@inproceedings{huttenlocher1983aaai-phonotactic,
  title     = {{Phonotactic and Lexical Constraints in Speech Recognition}},
  author    = {Huttenlocher, Daniel P. and Sue, Victor W.},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {1983},
  pages     = {172-176},
  url       = {https://mlanthology.org/aaai/1983/huttenlocher1983aaai-phonotactic/}
}