Large-vocabulary spoken word recognition using simplified time-warping patterns

Y. Nara, Kazuhiko Iwata, Y. Kijima, A. Kobayashi, S. Kimura, S. Sasaki, J. Tanahashi

Research output: Contribution to journalConference article

1 Citation (Scopus)

Abstract

We propose a new matching algorithm for large vocabulary spoken word recognition, which gives a recognition score compatible to that of the traditional DP matching algorithm, but requires less than 1/10 as much calculation. By a computer simulation of 1,000 categories in speaker dependent recognition of speech samples uttered by five male adult speakers, an average recognition score of 95.8% was obtained. We have constructed a real-time speaker dependent speech recognizer using our algorithm. We are now examining the application of this recognizer to Japanese text input.

Original languageEnglish
Article number1171514
Pages (from-to)1266-1269
Number of pages4
JournalICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume1982-May
DOIs
Publication statusPublished - 1982 Jan 1
Externally publishedYes
Event1982 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 1982 - Paris, France
Duration: 1982 May 31982 May 5

Fingerprint

Computer simulation

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Large-vocabulary spoken word recognition using simplified time-warping patterns. / Nara, Y.; Iwata, Kazuhiko; Kijima, Y.; Kobayashi, A.; Kimura, S.; Sasaki, S.; Tanahashi, J.

In: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, Vol. 1982-May, 1171514, 01.01.1982, p. 1266-1269.

Research output: Contribution to journalConference article

@article{fbbd3f48dbab4e8fa77350a7b63ec8ea,
title = "Large-vocabulary spoken word recognition using simplified time-warping patterns",
abstract = "We propose a new matching algorithm for large vocabulary spoken word recognition, which gives a recognition score compatible to that of the traditional DP matching algorithm, but requires less than 1/10 as much calculation. By a computer simulation of 1,000 categories in speaker dependent recognition of speech samples uttered by five male adult speakers, an average recognition score of 95.8{\%} was obtained. We have constructed a real-time speaker dependent speech recognizer using our algorithm. We are now examining the application of this recognizer to Japanese text input.",
author = "Y. Nara and Kazuhiko Iwata and Y. Kijima and A. Kobayashi and S. Kimura and S. Sasaki and J. Tanahashi",
year = "1982",
month = "1",
day = "1",
doi = "10.1109/ICASSP.1982.1171514",
language = "English",
volume = "1982-May",
pages = "1266--1269",
journal = "Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing",
issn = "0736-7791",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Large-vocabulary spoken word recognition using simplified time-warping patterns

AU - Nara, Y.

AU - Iwata, Kazuhiko

AU - Kijima, Y.

AU - Kobayashi, A.

AU - Kimura, S.

AU - Sasaki, S.

AU - Tanahashi, J.

PY - 1982/1/1

Y1 - 1982/1/1

N2 - We propose a new matching algorithm for large vocabulary spoken word recognition, which gives a recognition score compatible to that of the traditional DP matching algorithm, but requires less than 1/10 as much calculation. By a computer simulation of 1,000 categories in speaker dependent recognition of speech samples uttered by five male adult speakers, an average recognition score of 95.8% was obtained. We have constructed a real-time speaker dependent speech recognizer using our algorithm. We are now examining the application of this recognizer to Japanese text input.

AB - We propose a new matching algorithm for large vocabulary spoken word recognition, which gives a recognition score compatible to that of the traditional DP matching algorithm, but requires less than 1/10 as much calculation. By a computer simulation of 1,000 categories in speaker dependent recognition of speech samples uttered by five male adult speakers, an average recognition score of 95.8% was obtained. We have constructed a real-time speaker dependent speech recognizer using our algorithm. We are now examining the application of this recognizer to Japanese text input.

UR - http://www.scopus.com/inward/record.url?scp=84910794191&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84910794191&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.1982.1171514

DO - 10.1109/ICASSP.1982.1171514

M3 - Conference article

VL - 1982-May

SP - 1266

EP - 1269

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

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

SN - 0736-7791

M1 - 1171514

ER -