Continuous speech recognition by context-dependent phonetic HMM and an efficient algorithm for finding N-Best sentence hypotheses

Katunobu Itou, Satoru Hayamizu, Hozumi Tanaka

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

14 Citations (Scopus)

Abstract

In this paper, a continuous speech recognition system, "niNja" (Natural language INterface in JApanese), is presented. Efficient search algorithms are proposed to get high accuracy and to reduce the required computations. First, an LR parsing algorithm with context-dependent phone models is proposed. Second, scores of the same phone models in different hypotheses at the phone-level are represented by the single score of the best hypothesis. The system is tested for the task with 113 word vocabulary, word perplexity 4.1. It produces sentence accuracy of 97.3% for the 10 open speakers's 110 sentences and the error reduction is as much as 77% comparing with the case using context independent phone models.

Original languageEnglish
Title of host publicationICASSP 1992 - 1992 International Conference on Acoustics, Speech, and Signal Processing
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages21-24
Number of pages4
ISBN (Electronic)0780305329
DOIs
Publication statusPublished - 1992
Externally publishedYes
Event1992 International Conference on Acoustics, Speech, and Signal Processing, ICASSP 1992 - San Francisco, United States
Duration: 1992 Mar 231992 Mar 26

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume1
ISSN (Print)1520-6149

Other

Other1992 International Conference on Acoustics, Speech, and Signal Processing, ICASSP 1992
Country/TerritoryUnited States
CitySan Francisco
Period92/3/2392/3/26

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Continuous speech recognition by context-dependent phonetic HMM and an efficient algorithm for finding N-Best sentence hypotheses'. Together they form a unique fingerprint.

Cite this