AUTOMATIC LABELING OF KNOWN SPEECH SAMPLES USING A RULE-BASED NETWORK REPRESENTATION AND SEGMENTATION TECHNIQUE.

Kazuyo Tanaka, Satoru Hayamizu, Kozo Ohta

Research output: Contribution to journalArticlepeer-review

Abstract

An automatic labeling technique for known speech samples is proposed to construct a fine speech data base. A word (or sentence) is represented by a phonetic network which covers the acoustic variation contained in the utterances of the word (or sentence). An input speech sample is segmented using its parameter pattern dynamics and labeled to the optimal phonetic label (called APSEG) sequence by matching th segment sequence to the generated phonetic network using constrained dynamic programming. The feasibility of the method is confirmed when it is applied ot a word set containing 53 city names.

Original languageEnglish
Pages (from-to)30-37
Number of pages8
JournalDenshi Gijutsu Sogo Kenkyusho Iho/Bulletin of the Electrotechnical Laboratory
Volume52
Issue number3
Publication statusPublished - 1988
Externally publishedYes

ASJC Scopus subject areas

  • Condensed Matter Physics
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'AUTOMATIC LABELING OF KNOWN SPEECH SAMPLES USING A RULE-BASED NETWORK REPRESENTATION AND SEGMENTATION TECHNIQUE.'. Together they form a unique fingerprint.

Cite this