Speaker recognition using speaker-independent universal acoustic model and synchronous sensing for "Business Microscope"

Jun Nishimura, Tadahiro Kuroda

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

1 Citation (Scopus)

Abstract

"Business Microscope" visualizes interactions among knowledge workers in organization by sensing their face-to-face communication using sensornet. To analyze the workers' communication in detail speaker recognition for each node is needed In the conventional studies, specific speaker-dependent training samples and acoustic model are required to recognize each speaker. In this work, speaker recognition using speaker-independent universal acoustic model is proposed This method utilizes synchronous sensing of sensornet to extract the cepstral difference in acoustic channel and allows all speakers in the system to use same single acoustic model. The universal acoustic model constructed from 41 channel filterbank MFCC and large-sized LBG codebook achieved speaker recognition accuracy of 97.32% on test inputs of 0.2s for four speakers. With the synchronization error (<120ms) among sensor nodes, the drop in recognition accuracy of less than 2 pts is observed

Original languageEnglish
Title of host publication2009 4th International Symposium on Wireless and Pervasive Computing, ISWPC 2009
DOIs
Publication statusPublished - 2009
Event2009 4th International Symposium on Wireless and Pervasive Computing, ISWPC 2009 - Melbourne, VIC, Australia
Duration: 2009 Feb 112009 Feb 13

Other

Other2009 4th International Symposium on Wireless and Pervasive Computing, ISWPC 2009
CountryAustralia
CityMelbourne, VIC
Period09/2/1109/2/13

Fingerprint

Microscopes
Acoustics
Industry
Communication
Sensor nodes
Synchronization

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications
  • Software

Cite this

Nishimura, J., & Kuroda, T. (2009). Speaker recognition using speaker-independent universal acoustic model and synchronous sensing for "Business Microscope". In 2009 4th International Symposium on Wireless and Pervasive Computing, ISWPC 2009 [4800609] https://doi.org/10.1109/ISWPC.2009.4800609

Speaker recognition using speaker-independent universal acoustic model and synchronous sensing for "Business Microscope". / Nishimura, Jun; Kuroda, Tadahiro.

2009 4th International Symposium on Wireless and Pervasive Computing, ISWPC 2009. 2009. 4800609.

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

Nishimura, J & Kuroda, T 2009, Speaker recognition using speaker-independent universal acoustic model and synchronous sensing for "Business Microscope". in 2009 4th International Symposium on Wireless and Pervasive Computing, ISWPC 2009., 4800609, 2009 4th International Symposium on Wireless and Pervasive Computing, ISWPC 2009, Melbourne, VIC, Australia, 09/2/11. https://doi.org/10.1109/ISWPC.2009.4800609
Nishimura, Jun ; Kuroda, Tadahiro. / Speaker recognition using speaker-independent universal acoustic model and synchronous sensing for "Business Microscope". 2009 4th International Symposium on Wireless and Pervasive Computing, ISWPC 2009. 2009.
@inproceedings{7198d10bf94e42f394530d75a1beb48c,
title = "Speaker recognition using speaker-independent universal acoustic model and synchronous sensing for {"}Business Microscope{"}",
abstract = "{"}Business Microscope{"} visualizes interactions among knowledge workers in organization by sensing their face-to-face communication using sensornet. To analyze the workers' communication in detail speaker recognition for each node is needed In the conventional studies, specific speaker-dependent training samples and acoustic model are required to recognize each speaker. In this work, speaker recognition using speaker-independent universal acoustic model is proposed This method utilizes synchronous sensing of sensornet to extract the cepstral difference in acoustic channel and allows all speakers in the system to use same single acoustic model. The universal acoustic model constructed from 41 channel filterbank MFCC and large-sized LBG codebook achieved speaker recognition accuracy of 97.32{\%} on test inputs of 0.2s for four speakers. With the synchronization error (<120ms) among sensor nodes, the drop in recognition accuracy of less than 2 pts is observed",
author = "Jun Nishimura and Tadahiro Kuroda",
year = "2009",
doi = "10.1109/ISWPC.2009.4800609",
language = "English",
isbn = "9781424429660",
booktitle = "2009 4th International Symposium on Wireless and Pervasive Computing, ISWPC 2009",

}

TY - GEN

T1 - Speaker recognition using speaker-independent universal acoustic model and synchronous sensing for "Business Microscope"

AU - Nishimura, Jun

AU - Kuroda, Tadahiro

PY - 2009

Y1 - 2009

N2 - "Business Microscope" visualizes interactions among knowledge workers in organization by sensing their face-to-face communication using sensornet. To analyze the workers' communication in detail speaker recognition for each node is needed In the conventional studies, specific speaker-dependent training samples and acoustic model are required to recognize each speaker. In this work, speaker recognition using speaker-independent universal acoustic model is proposed This method utilizes synchronous sensing of sensornet to extract the cepstral difference in acoustic channel and allows all speakers in the system to use same single acoustic model. The universal acoustic model constructed from 41 channel filterbank MFCC and large-sized LBG codebook achieved speaker recognition accuracy of 97.32% on test inputs of 0.2s for four speakers. With the synchronization error (<120ms) among sensor nodes, the drop in recognition accuracy of less than 2 pts is observed

AB - "Business Microscope" visualizes interactions among knowledge workers in organization by sensing their face-to-face communication using sensornet. To analyze the workers' communication in detail speaker recognition for each node is needed In the conventional studies, specific speaker-dependent training samples and acoustic model are required to recognize each speaker. In this work, speaker recognition using speaker-independent universal acoustic model is proposed This method utilizes synchronous sensing of sensornet to extract the cepstral difference in acoustic channel and allows all speakers in the system to use same single acoustic model. The universal acoustic model constructed from 41 channel filterbank MFCC and large-sized LBG codebook achieved speaker recognition accuracy of 97.32% on test inputs of 0.2s for four speakers. With the synchronization error (<120ms) among sensor nodes, the drop in recognition accuracy of less than 2 pts is observed

UR - http://www.scopus.com/inward/record.url?scp=65249106057&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=65249106057&partnerID=8YFLogxK

U2 - 10.1109/ISWPC.2009.4800609

DO - 10.1109/ISWPC.2009.4800609

M3 - Conference contribution

AN - SCOPUS:65249106057

SN - 9781424429660

BT - 2009 4th International Symposium on Wireless and Pervasive Computing, ISWPC 2009

ER -