Understanding three simultaneous speeches

Hiroshi G. Okuno, Tomohiro Nakatani, Takeshi Kawabata

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

6 Citations (Scopus)

Abstract

Understanding three simultaneous speeches is proposed as a challenge problem to foster artificial intelligence, speech and sound understanding or recognition, and computational auditory scene analysis research. Automatic speech recognition under noisy environments is attacked by speech enhancement techniques such as noise reduction and speaker adaptation. However, the signal-to-noise ratio of speech in two simultaneous speeches is too poor to apply these techniques. Therefore, novel techniques need to be developed. One candidate is to use speech stream segregation as a front-end of automatic speech recognition systems. Preliminary experiments on understanding two simultaneous speeches show that the proposed challenge problem will be feasible with speech stream segregation. The detailed plan of the research on and benchmark sounds for the proposed challenge problem is also presented.

Original languageEnglish
Title of host publicationIJCAI International Joint Conference on Artificial Intelligence
Pages30-35
Number of pages6
Volume1
Publication statusPublished - 1997
Externally publishedYes
Event15th International Joint Conference on Artificial Intelligence, IJCAI 1997 - Nagoya, Aichi, Japan
Duration: 1997 Aug 231997 Aug 29

Other

Other15th International Joint Conference on Artificial Intelligence, IJCAI 1997
CountryJapan
CityNagoya, Aichi
Period97/8/2397/8/29

Fingerprint

Speech recognition
Acoustic waves
Speech enhancement
Noise abatement
Artificial intelligence
Signal to noise ratio
Experiments

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Okuno, H. G., Nakatani, T., & Kawabata, T. (1997). Understanding three simultaneous speeches. In IJCAI International Joint Conference on Artificial Intelligence (Vol. 1, pp. 30-35)

Understanding three simultaneous speeches. / Okuno, Hiroshi G.; Nakatani, Tomohiro; Kawabata, Takeshi.

IJCAI International Joint Conference on Artificial Intelligence. Vol. 1 1997. p. 30-35.

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

Okuno, HG, Nakatani, T & Kawabata, T 1997, Understanding three simultaneous speeches. in IJCAI International Joint Conference on Artificial Intelligence. vol. 1, pp. 30-35, 15th International Joint Conference on Artificial Intelligence, IJCAI 1997, Nagoya, Aichi, Japan, 97/8/23.
Okuno HG, Nakatani T, Kawabata T. Understanding three simultaneous speeches. In IJCAI International Joint Conference on Artificial Intelligence. Vol. 1. 1997. p. 30-35
Okuno, Hiroshi G. ; Nakatani, Tomohiro ; Kawabata, Takeshi. / Understanding three simultaneous speeches. IJCAI International Joint Conference on Artificial Intelligence. Vol. 1 1997. pp. 30-35
@inproceedings{48366a60c7484886816e58cff26d2904,
title = "Understanding three simultaneous speeches",
abstract = "Understanding three simultaneous speeches is proposed as a challenge problem to foster artificial intelligence, speech and sound understanding or recognition, and computational auditory scene analysis research. Automatic speech recognition under noisy environments is attacked by speech enhancement techniques such as noise reduction and speaker adaptation. However, the signal-to-noise ratio of speech in two simultaneous speeches is too poor to apply these techniques. Therefore, novel techniques need to be developed. One candidate is to use speech stream segregation as a front-end of automatic speech recognition systems. Preliminary experiments on understanding two simultaneous speeches show that the proposed challenge problem will be feasible with speech stream segregation. The detailed plan of the research on and benchmark sounds for the proposed challenge problem is also presented.",
author = "Okuno, {Hiroshi G.} and Tomohiro Nakatani and Takeshi Kawabata",
year = "1997",
language = "English",
volume = "1",
pages = "30--35",
booktitle = "IJCAI International Joint Conference on Artificial Intelligence",

}

TY - GEN

T1 - Understanding three simultaneous speeches

AU - Okuno, Hiroshi G.

AU - Nakatani, Tomohiro

AU - Kawabata, Takeshi

PY - 1997

Y1 - 1997

N2 - Understanding three simultaneous speeches is proposed as a challenge problem to foster artificial intelligence, speech and sound understanding or recognition, and computational auditory scene analysis research. Automatic speech recognition under noisy environments is attacked by speech enhancement techniques such as noise reduction and speaker adaptation. However, the signal-to-noise ratio of speech in two simultaneous speeches is too poor to apply these techniques. Therefore, novel techniques need to be developed. One candidate is to use speech stream segregation as a front-end of automatic speech recognition systems. Preliminary experiments on understanding two simultaneous speeches show that the proposed challenge problem will be feasible with speech stream segregation. The detailed plan of the research on and benchmark sounds for the proposed challenge problem is also presented.

AB - Understanding three simultaneous speeches is proposed as a challenge problem to foster artificial intelligence, speech and sound understanding or recognition, and computational auditory scene analysis research. Automatic speech recognition under noisy environments is attacked by speech enhancement techniques such as noise reduction and speaker adaptation. However, the signal-to-noise ratio of speech in two simultaneous speeches is too poor to apply these techniques. Therefore, novel techniques need to be developed. One candidate is to use speech stream segregation as a front-end of automatic speech recognition systems. Preliminary experiments on understanding two simultaneous speeches show that the proposed challenge problem will be feasible with speech stream segregation. The detailed plan of the research on and benchmark sounds for the proposed challenge problem is also presented.

UR - http://www.scopus.com/inward/record.url?scp=79955064007&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79955064007&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:79955064007

VL - 1

SP - 30

EP - 35

BT - IJCAI International Joint Conference on Artificial Intelligence

ER -