Skip to main content
Article
The Lexical Access Component of the CMU Continuous Speech Recognition System
Proceedings of the Intl. Conf. on Acoustics, Speech, and Signal Processing
  • Alexander I Rudnicky, Carnegie Mellon University
  • Lynn K Baurneister, Carnegie Mellon University
  • Kevin H DeGraaf, Carnegie Mellon University
  • Eric Lehmann, Carnegie Mellon University
Date of Original Version
1-1-1987
Type
Conference Proceeding
Rights Management
Authorized licensed use limited to: Carnegie Mellon Libraries.
Abstract or Description

The CMU Lexical Access system hypothesizes words from a phonetic lattice, supplemented by a coarse labelling of the speech signal. Word hypotheses are anchored on syllabic nuclei and are generated independently for different parts of the utterance. Junctures between words are resolved separately, on demand from the Parser module. The lexical representation is generated by rule from base foms , in a completely automatic process. A description of the various components of the system is provided, a s well a s performance data.

Citation Information
Alexander I Rudnicky, Lynn K Baurneister, Kevin H DeGraaf and Eric Lehmann. "The Lexical Access Component of the CMU Continuous Speech Recognition System" Proceedings of the Intl. Conf. on Acoustics, Speech, and Signal Processing (1987) p. 376 - 379
Available at: http://works.bepress.com/alexander_rudnicky/51/