Neural tree network for speech segmentation into subword acoustic units

Manish Sharma, Richard J. Mammone

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A novel method of segmenting un-transcribed speech into sub-word acoustic units using neural tree networks (NTN) is presented. A NTN is a hierarchical classifier that combines the properties of decision trees and feed-forward neural networks. Segmentation of speech into sub-word units (of acoustic significance) is vital for large vocabulary, continuous speech recognition on un-transcribed speech database.

Original languageAmerican English
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
EditorsJames L. Flanagan, Richard J. Mammone, Albert E. Brandenstein, Edward R. Pike, Stelios C.A. Thomopoulos, al et al
PublisherPubl by Society of Photo-Optical Instrumentation Engineers
Pages2-7
Number of pages6
ISBN (Print)0819413666
StatePublished - 1994
EventSubstance Identification Analytics - Innsbruck, Austria
Duration: Oct 4 1993Oct 8 1993

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume2093

Other

OtherSubstance Identification Analytics
CityInnsbruck, Austria
Period10/4/9310/8/93

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this