Accession Number : ADA254747


Title :   Transputer Implementation of the TRACE Model of Speech Recognition


Descriptive Note : Final rept. 1 May 1987-31 Mar 1992


Corporate Author : CALIFORNIA UNIV SAN DIEGO LA JOLLA CENTER FOR RESEARCH IN LANGUAGE


Personal Author(s) : Elman, Jeffrey L ; Smith, Paul S ; Dolson, Mark


Full Text : https://apps.dtic.mil/dtic/tr/fulltext/u2/a254747.pdf


Report Date : Aug 1992


Pagination or Media Count : 24


Abstract : We describe the accomplishments of the five-year project to develop an extended version of the TRACE model of speech recognition and to port it to a Transputer platform. We begin with an over view of the project. We then describe the TRACE Model. TRACE is an artificial neural network which attempts to model the processing of speech from acoustic input to word extraction, in a manner consistent with what is known of human perceptual abilities. Following that, we discuss the work done to extend and develop the model in the direction of real- time performance with an extended phonemic inventory. This includes algorithm changes to TRACE, software for managing the Transputer processors, a new acoustic/phonetic front-end, debugging and testing tools, and graphics visualization software.


Descriptors :   *NEURAL NETS , *PARALLEL PROCESSING , *SPEECH RECOGNITION , ALGORITHMS , MODELS , REAL TIME , TOOLS , PLATFORMS , EXTRACTION , PHONETICS , SPEECH , WORK , INVENTORY , ACOUSTICS , RECOGNITION , GRAPHICS , TIME , PROCESSING , HUMANS , NETWORKS , INPUT


Subject Categories : Computer Systems
      Voice Communications


Distribution Statement : APPROVED FOR PUBLIC RELEASE