COMPARISON OF THE PARAMETERS UTILIZED IN RECOGNIZING CONTINUOUS SPEECH BY USING CONTINUOUS DYNAMIC PROGRAMMING.

Satoru Hayamizu*, Ryu ichi Oka

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

The five feature parameters, vocal tract area functions, PARCOR coefficients, FET cepstrum, LPC cepstrum and Weighted Likelihood Ratio (WLR), are compared in recognition experiments Using Continuous Dynamic Programming (CDP). The post processing of the CDP which makes a word lattice is used and no syntactical constraints are introduced. The speech materials analyzed are the continuous utterances of 54 principal city names. The highest discrimination rates are obtained with LPC cepstrum (97. 8%) and WLR (97. 4%).

Original languageEnglish
Pages (from-to)90-93
Number of pages4
JournalBulletin of the Electrotechnical Laboratory, Tokyo
Volume48
Issue number1-2
Publication statusPublished - 1984
Externally publishedYes

ASJC Scopus subject areas

  • Engineering(all)

Fingerprint

Dive into the research topics of 'COMPARISON OF THE PARAMETERS UTILIZED IN RECOGNIZING CONTINUOUS SPEECH BY USING CONTINUOUS DYNAMIC PROGRAMMING.'. Together they form a unique fingerprint.

Cite this