Computational auditory scene analysis and its application to robot audition

Hiroshi G. Okuno; Kazuhiro Nakadai

doi:10.1109/HSCMA.2008.4538702

Computational auditory scene analysis and its application to robot audition

Hiroshi G. Okuno, Kazuhiro Nakadai

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

9 Citations (Scopus)

Abstract

Robot capability of hearing sounds, in particular, a mixture of sounds, by its own microphones, that is, robot audition, is important in improving human robot interaction. This paper presents the robot audition open-source software, called "HARK" (HRI-JP Audition for Robots with Kyoto University), which consists of primitive functions in computational auditory scene analysis; sound source localization, separation, and recognition of separated sounds. Since separated sounds suffer from spectral distortion due to separation, the HARK generates a time-spectral map of reliability, called "missing feature mask", for features of separated sounds. Then separated sounds are recognized by the Missing-Feature Theory (MFT) based ASR with missing feature masks. The HARK is implemented on the middleware called "FlowDesigner" to share intermediate audio data, which enables near real-time processing.

Original language	English
Title of host publication	2008 Hands-free Speech Communication and Microphone Arrays, Proceedings, HSCMA 2008
Pages	124-127
Number of pages	4
DOIs	https://doi.org/10.1109/HSCMA.2008.4538702
Publication status	Published - 2008
Externally published	Yes
Event	2008 Hands-free Speech Communication and Microphone Arrays, HSCMA 2008 - Trento Duration: 2008 May 6 → 2008 May 8

Other

Other	2008 Hands-free Speech Communication and Microphone Arrays, HSCMA 2008
City	Trento
Period	08/5/6 → 08/5/8

Keywords

Computational auditory scene analysis
Missing feature theory
Robot audition
Simultaneous speakers

ASJC Scopus subject areas

Hardware and Architecture
Electrical and Electronic Engineering
Communication

Access to Document

10.1109/HSCMA.2008.4538702

Cite this

@inproceedings{a4f94496f3e8458c897c391c165568d5,

title = "Computational auditory scene analysis and its application to robot audition",

abstract = "Robot capability of hearing sounds, in particular, a mixture of sounds, by its own microphones, that is, robot audition, is important in improving human robot interaction. This paper presents the robot audition open-source software, called {"}HARK{"} (HRI-JP Audition for Robots with Kyoto University), which consists of primitive functions in computational auditory scene analysis; sound source localization, separation, and recognition of separated sounds. Since separated sounds suffer from spectral distortion due to separation, the HARK generates a time-spectral map of reliability, called {"}missing feature mask{"}, for features of separated sounds. Then separated sounds are recognized by the Missing-Feature Theory (MFT) based ASR with missing feature masks. The HARK is implemented on the middleware called {"}FlowDesigner{"} to share intermediate audio data, which enables near real-time processing.",

keywords = "Computational auditory scene analysis, Missing feature theory, Robot audition, Simultaneous speakers",

author = "Okuno, {Hiroshi G.} and Kazuhiro Nakadai",

year = "2008",

doi = "10.1109/HSCMA.2008.4538702",

language = "English",

isbn = "9781424423385",

pages = "124--127",

booktitle = "2008 Hands-free Speech Communication and Microphone Arrays, Proceedings, HSCMA 2008",

note = "2008 Hands-free Speech Communication and Microphone Arrays, HSCMA 2008 ; Conference date: 06-05-2008 Through 08-05-2008",

}

TY - GEN

T1 - Computational auditory scene analysis and its application to robot audition

AU - Okuno, Hiroshi G.

AU - Nakadai, Kazuhiro

PY - 2008

Y1 - 2008

N2 - Robot capability of hearing sounds, in particular, a mixture of sounds, by its own microphones, that is, robot audition, is important in improving human robot interaction. This paper presents the robot audition open-source software, called "HARK" (HRI-JP Audition for Robots with Kyoto University), which consists of primitive functions in computational auditory scene analysis; sound source localization, separation, and recognition of separated sounds. Since separated sounds suffer from spectral distortion due to separation, the HARK generates a time-spectral map of reliability, called "missing feature mask", for features of separated sounds. Then separated sounds are recognized by the Missing-Feature Theory (MFT) based ASR with missing feature masks. The HARK is implemented on the middleware called "FlowDesigner" to share intermediate audio data, which enables near real-time processing.

AB - Robot capability of hearing sounds, in particular, a mixture of sounds, by its own microphones, that is, robot audition, is important in improving human robot interaction. This paper presents the robot audition open-source software, called "HARK" (HRI-JP Audition for Robots with Kyoto University), which consists of primitive functions in computational auditory scene analysis; sound source localization, separation, and recognition of separated sounds. Since separated sounds suffer from spectral distortion due to separation, the HARK generates a time-spectral map of reliability, called "missing feature mask", for features of separated sounds. Then separated sounds are recognized by the Missing-Feature Theory (MFT) based ASR with missing feature masks. The HARK is implemented on the middleware called "FlowDesigner" to share intermediate audio data, which enables near real-time processing.

KW - Computational auditory scene analysis

KW - Missing feature theory

KW - Robot audition

KW - Simultaneous speakers

UR - http://www.scopus.com/inward/record.url?scp=50449106910&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=50449106910&partnerID=8YFLogxK

U2 - 10.1109/HSCMA.2008.4538702

DO - 10.1109/HSCMA.2008.4538702

M3 - Conference contribution

AN - SCOPUS:50449106910

SN - 9781424423385

SP - 124

EP - 127

BT - 2008 Hands-free Speech Communication and Microphone Arrays, Proceedings, HSCMA 2008

T2 - 2008 Hands-free Speech Communication and Microphone Arrays, HSCMA 2008

Y2 - 6 May 2008 through 8 May 2008

ER -

Computational auditory scene analysis and its application to robot audition

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this