Recognition of three simultaneous utterance of speech by four-line directivity microphone mounted on head of robot

Naoya Mochiki; Toshiyuki Sekiya; Tetsuji Ogawa; Tetsunori Kobayashi

Recognition of three simultaneous utterance of speech by four-line directivity microphone mounted on head of robot

Naoya Mochiki, Toshiyuki Sekiya, Tetsuji Ogawa, Tetsunori Kobayashi

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

Abstract

A sound source separation method using four-line directivity microphones mounted on a head of a robot is proposed and applied to speech recognition under existence of two disturbances of speech. Sound source separation methods using microphones mounted on robot heads generally used strict head-related transfer functions(HRTF). We propose a robust sound source separation that does not require an estimate of a strict HRTF. Our method takes advantage of a sound pressure difference with the robot head acting as a sound barrier. The enhancement of the difference in the target speech is performed by signal processing of three layers:two-line SAFIA, two-line Spectral Subtraction and their integration. The experimental results of three simultaneous utterance recognition with vocabulary of 20K show that the proposed method is effective in achieving 71% error reduction.

Original language	English
Title of host publication	8th International Conference on Spoken Language Processing, ICSLP 2004
Publisher	International Speech Communication Association
Pages	821-824
Number of pages	4
Publication status	Published - 2004
Event	8th International Conference on Spoken Language Processing, ICSLP 2004 - Jeju, Jeju Island, Korea, Republic of Duration: 2004 Oct 4 → 2004 Oct 8

Other

Other	8th International Conference on Spoken Language Processing, ICSLP 2004
Country/Territory	Korea, Republic of
City	Jeju, Jeju Island
Period	04/10/4 → 04/10/8

ASJC Scopus subject areas

Language and Linguistics
Linguistics and Language

Cite this

Recognition of three simultaneous utterance of speech by four-line directivity microphone mounted on head of robot. / Mochiki, Naoya; Sekiya, Toshiyuki; Ogawa, Tetsuji et al.
8th International Conference on Spoken Language Processing, ICSLP 2004. International Speech Communication Association, 2004. p. 821-824.

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

Mochiki, N, Sekiya, T, Ogawa, T & Kobayashi, T 2004, Recognition of three simultaneous utterance of speech by four-line directivity microphone mounted on head of robot. in 8th International Conference on Spoken Language Processing, ICSLP 2004. International Speech Communication Association, pp. 821-824, 8th International Conference on Spoken Language Processing, ICSLP 2004, Jeju, Jeju Island, Korea, Republic of, 04/10/4.

@inproceedings{bb942d155a3243c29b3aa2b187c14401,

title = "Recognition of three simultaneous utterance of speech by four-line directivity microphone mounted on head of robot",

abstract = "A sound source separation method using four-line directivity microphones mounted on a head of a robot is proposed and applied to speech recognition under existence of two disturbances of speech. Sound source separation methods using microphones mounted on robot heads generally used strict head-related transfer functions(HRTF). We propose a robust sound source separation that does not require an estimate of a strict HRTF. Our method takes advantage of a sound pressure difference with the robot head acting as a sound barrier. The enhancement of the difference in the target speech is performed by signal processing of three layers:two-line SAFIA, two-line Spectral Subtraction and their integration. The experimental results of three simultaneous utterance recognition with vocabulary of 20K show that the proposed method is effective in achieving 71% error reduction.",

author = "Naoya Mochiki and Toshiyuki Sekiya and Tetsuji Ogawa and Tetsunori Kobayashi",

year = "2004",

language = "English",

pages = "821--824",

booktitle = "8th International Conference on Spoken Language Processing, ICSLP 2004",

publisher = "International Speech Communication Association",

note = "8th International Conference on Spoken Language Processing, ICSLP 2004 ; Conference date: 04-10-2004 Through 08-10-2004",

}

TY - GEN

T1 - Recognition of three simultaneous utterance of speech by four-line directivity microphone mounted on head of robot

AU - Mochiki, Naoya

AU - Sekiya, Toshiyuki

AU - Ogawa, Tetsuji

AU - Kobayashi, Tetsunori

PY - 2004

Y1 - 2004

N2 - A sound source separation method using four-line directivity microphones mounted on a head of a robot is proposed and applied to speech recognition under existence of two disturbances of speech. Sound source separation methods using microphones mounted on robot heads generally used strict head-related transfer functions(HRTF). We propose a robust sound source separation that does not require an estimate of a strict HRTF. Our method takes advantage of a sound pressure difference with the robot head acting as a sound barrier. The enhancement of the difference in the target speech is performed by signal processing of three layers:two-line SAFIA, two-line Spectral Subtraction and their integration. The experimental results of three simultaneous utterance recognition with vocabulary of 20K show that the proposed method is effective in achieving 71% error reduction.

AB - A sound source separation method using four-line directivity microphones mounted on a head of a robot is proposed and applied to speech recognition under existence of two disturbances of speech. Sound source separation methods using microphones mounted on robot heads generally used strict head-related transfer functions(HRTF). We propose a robust sound source separation that does not require an estimate of a strict HRTF. Our method takes advantage of a sound pressure difference with the robot head acting as a sound barrier. The enhancement of the difference in the target speech is performed by signal processing of three layers:two-line SAFIA, two-line Spectral Subtraction and their integration. The experimental results of three simultaneous utterance recognition with vocabulary of 20K show that the proposed method is effective in achieving 71% error reduction.

UR - http://www.scopus.com/inward/record.url?scp=85009121653&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85009121653&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85009121653

SP - 821

EP - 824

BT - 8th International Conference on Spoken Language Processing, ICSLP 2004

PB - International Speech Communication Association

T2 - 8th International Conference on Spoken Language Processing, ICSLP 2004

Y2 - 4 October 2004 through 8 October 2004

ER -

Recognition of three simultaneous utterance of speech by four-line directivity microphone mounted on head of robot

Abstract

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this