Auditory stream segregation in auditory scene analysis with a multi-agent system

Tomohiro Nakatani, Hiroshi G. Okuno, Takeshi Kawabata

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

14 Citations (Scopus)

Abstract

We propose a novel approach to auditory stream segregation which extracts individual sounds (auditory stream) from a mixture of sounds in auditory scene analysis. The HBSS (Harmonic-Based Stream Segregation) system is designed and developed by employing a multi-agent system. HBSS uses only harmonics as a clue to segregation and extracts auditory streams incrementally. When the tracer-generator agent detects a new sound, it spawns a tracer agent, which extracts an auditory stream by tracing its harmonic structure. The tracer sends a feedforward signal so that the generator and other tracers should not work on the same stream that is being traced. The quality of segregation may be poor due to redundant and ghost tracers. HBSS copes with this problem by introducing monitor agents, which detect and eliminate redundant and ghost tracers. HBSS can segregate two streams from a mixture of man's and woman's speech. It is easy to resynthesize speech or sounds from the corresponding streams. Additionally, HBSS can be easily extended by adding agents of a new capability. HBSS can be considered as the first step to computational auditory scene analysis.

Original languageEnglish
Title of host publicationProceedings of the National Conference on Artificial Intelligence
Place of PublicationMenlo Park, CA, United States
PublisherAAAI
Pages100-107
Number of pages8
Volume1
Publication statusPublished - 1994
Externally publishedYes
EventProceedings of the 12th National Conference on Artificial Intelligence. Part 1 (of 2) - Seattle, WA, USA
Duration: 1994 Jul 311994 Aug 4

Other

OtherProceedings of the 12th National Conference on Artificial Intelligence. Part 1 (of 2)
CitySeattle, WA, USA
Period94/7/3194/8/4

Fingerprint

Multi agent systems
Acoustic waves

ASJC Scopus subject areas

  • Software

Cite this

Nakatani, T., Okuno, H. G., & Kawabata, T. (1994). Auditory stream segregation in auditory scene analysis with a multi-agent system. In Proceedings of the National Conference on Artificial Intelligence (Vol. 1, pp. 100-107). Menlo Park, CA, United States: AAAI.

Auditory stream segregation in auditory scene analysis with a multi-agent system. / Nakatani, Tomohiro; Okuno, Hiroshi G.; Kawabata, Takeshi.

Proceedings of the National Conference on Artificial Intelligence. Vol. 1 Menlo Park, CA, United States : AAAI, 1994. p. 100-107.

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

Nakatani, T, Okuno, HG & Kawabata, T 1994, Auditory stream segregation in auditory scene analysis with a multi-agent system. in Proceedings of the National Conference on Artificial Intelligence. vol. 1, AAAI, Menlo Park, CA, United States, pp. 100-107, Proceedings of the 12th National Conference on Artificial Intelligence. Part 1 (of 2), Seattle, WA, USA, 94/7/31.
Nakatani T, Okuno HG, Kawabata T. Auditory stream segregation in auditory scene analysis with a multi-agent system. In Proceedings of the National Conference on Artificial Intelligence. Vol. 1. Menlo Park, CA, United States: AAAI. 1994. p. 100-107
Nakatani, Tomohiro ; Okuno, Hiroshi G. ; Kawabata, Takeshi. / Auditory stream segregation in auditory scene analysis with a multi-agent system. Proceedings of the National Conference on Artificial Intelligence. Vol. 1 Menlo Park, CA, United States : AAAI, 1994. pp. 100-107
@inproceedings{e71c4471716c47648d3e1068e73c9b30,
title = "Auditory stream segregation in auditory scene analysis with a multi-agent system",
abstract = "We propose a novel approach to auditory stream segregation which extracts individual sounds (auditory stream) from a mixture of sounds in auditory scene analysis. The HBSS (Harmonic-Based Stream Segregation) system is designed and developed by employing a multi-agent system. HBSS uses only harmonics as a clue to segregation and extracts auditory streams incrementally. When the tracer-generator agent detects a new sound, it spawns a tracer agent, which extracts an auditory stream by tracing its harmonic structure. The tracer sends a feedforward signal so that the generator and other tracers should not work on the same stream that is being traced. The quality of segregation may be poor due to redundant and ghost tracers. HBSS copes with this problem by introducing monitor agents, which detect and eliminate redundant and ghost tracers. HBSS can segregate two streams from a mixture of man's and woman's speech. It is easy to resynthesize speech or sounds from the corresponding streams. Additionally, HBSS can be easily extended by adding agents of a new capability. HBSS can be considered as the first step to computational auditory scene analysis.",
author = "Tomohiro Nakatani and Okuno, {Hiroshi G.} and Takeshi Kawabata",
year = "1994",
language = "English",
volume = "1",
pages = "100--107",
booktitle = "Proceedings of the National Conference on Artificial Intelligence",
publisher = "AAAI",

}

TY - GEN

T1 - Auditory stream segregation in auditory scene analysis with a multi-agent system

AU - Nakatani, Tomohiro

AU - Okuno, Hiroshi G.

AU - Kawabata, Takeshi

PY - 1994

Y1 - 1994

N2 - We propose a novel approach to auditory stream segregation which extracts individual sounds (auditory stream) from a mixture of sounds in auditory scene analysis. The HBSS (Harmonic-Based Stream Segregation) system is designed and developed by employing a multi-agent system. HBSS uses only harmonics as a clue to segregation and extracts auditory streams incrementally. When the tracer-generator agent detects a new sound, it spawns a tracer agent, which extracts an auditory stream by tracing its harmonic structure. The tracer sends a feedforward signal so that the generator and other tracers should not work on the same stream that is being traced. The quality of segregation may be poor due to redundant and ghost tracers. HBSS copes with this problem by introducing monitor agents, which detect and eliminate redundant and ghost tracers. HBSS can segregate two streams from a mixture of man's and woman's speech. It is easy to resynthesize speech or sounds from the corresponding streams. Additionally, HBSS can be easily extended by adding agents of a new capability. HBSS can be considered as the first step to computational auditory scene analysis.

AB - We propose a novel approach to auditory stream segregation which extracts individual sounds (auditory stream) from a mixture of sounds in auditory scene analysis. The HBSS (Harmonic-Based Stream Segregation) system is designed and developed by employing a multi-agent system. HBSS uses only harmonics as a clue to segregation and extracts auditory streams incrementally. When the tracer-generator agent detects a new sound, it spawns a tracer agent, which extracts an auditory stream by tracing its harmonic structure. The tracer sends a feedforward signal so that the generator and other tracers should not work on the same stream that is being traced. The quality of segregation may be poor due to redundant and ghost tracers. HBSS copes with this problem by introducing monitor agents, which detect and eliminate redundant and ghost tracers. HBSS can segregate two streams from a mixture of man's and woman's speech. It is easy to resynthesize speech or sounds from the corresponding streams. Additionally, HBSS can be easily extended by adding agents of a new capability. HBSS can be considered as the first step to computational auditory scene analysis.

UR - http://www.scopus.com/inward/record.url?scp=0028565940&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028565940&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0028565940

VL - 1

SP - 100

EP - 107

BT - Proceedings of the National Conference on Artificial Intelligence

PB - AAAI

CY - Menlo Park, CA, United States

ER -