PROPOSAL OF A KNOWLEDGE BASED ISOLATED WORD RECOGNITION.

Shigeo Morishima, Hiroshi Harashima, Hiroshi Miyakawa

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

5 Citations (Scopus)

Abstract

The authors describe a knowledge-based isolated Japanese word recognition algorithm. The program is written in Prolog/KR and has two basic inference processes: a bottom-up search and a top-down search. In the bottom-up process, segmentation and vowel decision are performed and some target word patterns are generated. The top-down process includes a consonant decision using a score for each candidate word calculated on the basis of fuzzy set theory. In the vowel inference step, a template matching is applied. In the segmentation step, heuristic rules based on the spectrum transition and the wave form are used. In the consonant inference step, each rule has a hierarchical structure and the consonant is defined automatically in the form of a multivalued threshold function from learning data.

Original languageEnglish
Title of host publicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
PublisherIEEE
Pages713-716
Number of pages4
Publication statusPublished - 1986
Externally publishedYes

Fingerprint

Template matching
Fuzzy set theory
inference
proposals
vowels
Prolog (programming language)
fuzzy sets
learning
set theory
templates
thresholds

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering
  • Acoustics and Ultrasonics

Cite this

Morishima, S., Harashima, H., & Miyakawa, H. (1986). PROPOSAL OF A KNOWLEDGE BASED ISOLATED WORD RECOGNITION. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (pp. 713-716). IEEE.

PROPOSAL OF A KNOWLEDGE BASED ISOLATED WORD RECOGNITION. / Morishima, Shigeo; Harashima, Hiroshi; Miyakawa, Hiroshi.

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. IEEE, 1986. p. 713-716.

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

Morishima, S, Harashima, H & Miyakawa, H 1986, PROPOSAL OF A KNOWLEDGE BASED ISOLATED WORD RECOGNITION. in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. IEEE, pp. 713-716.
Morishima S, Harashima H, Miyakawa H. PROPOSAL OF A KNOWLEDGE BASED ISOLATED WORD RECOGNITION. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. IEEE. 1986. p. 713-716
Morishima, Shigeo ; Harashima, Hiroshi ; Miyakawa, Hiroshi. / PROPOSAL OF A KNOWLEDGE BASED ISOLATED WORD RECOGNITION. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. IEEE, 1986. pp. 713-716
@inproceedings{185f3b2cb1ed4e32821b1c6cd7ce47e7,
title = "PROPOSAL OF A KNOWLEDGE BASED ISOLATED WORD RECOGNITION.",
abstract = "The authors describe a knowledge-based isolated Japanese word recognition algorithm. The program is written in Prolog/KR and has two basic inference processes: a bottom-up search and a top-down search. In the bottom-up process, segmentation and vowel decision are performed and some target word patterns are generated. The top-down process includes a consonant decision using a score for each candidate word calculated on the basis of fuzzy set theory. In the vowel inference step, a template matching is applied. In the segmentation step, heuristic rules based on the spectrum transition and the wave form are used. In the consonant inference step, each rule has a hierarchical structure and the consonant is defined automatically in the form of a multivalued threshold function from learning data.",
author = "Shigeo Morishima and Hiroshi Harashima and Hiroshi Miyakawa",
year = "1986",
language = "English",
pages = "713--716",
booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "IEEE",

}

TY - GEN

T1 - PROPOSAL OF A KNOWLEDGE BASED ISOLATED WORD RECOGNITION.

AU - Morishima, Shigeo

AU - Harashima, Hiroshi

AU - Miyakawa, Hiroshi

PY - 1986

Y1 - 1986

N2 - The authors describe a knowledge-based isolated Japanese word recognition algorithm. The program is written in Prolog/KR and has two basic inference processes: a bottom-up search and a top-down search. In the bottom-up process, segmentation and vowel decision are performed and some target word patterns are generated. The top-down process includes a consonant decision using a score for each candidate word calculated on the basis of fuzzy set theory. In the vowel inference step, a template matching is applied. In the segmentation step, heuristic rules based on the spectrum transition and the wave form are used. In the consonant inference step, each rule has a hierarchical structure and the consonant is defined automatically in the form of a multivalued threshold function from learning data.

AB - The authors describe a knowledge-based isolated Japanese word recognition algorithm. The program is written in Prolog/KR and has two basic inference processes: a bottom-up search and a top-down search. In the bottom-up process, segmentation and vowel decision are performed and some target word patterns are generated. The top-down process includes a consonant decision using a score for each candidate word calculated on the basis of fuzzy set theory. In the vowel inference step, a template matching is applied. In the segmentation step, heuristic rules based on the spectrum transition and the wave form are used. In the consonant inference step, each rule has a hierarchical structure and the consonant is defined automatically in the form of a multivalued threshold function from learning data.

UR - http://www.scopus.com/inward/record.url?scp=0022868840&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0022868840&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0022868840

SP - 713

EP - 716

BT - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

PB - IEEE

ER -