Presentation 2015-03-03
Multi-modal Source Number Estimation in Multi-party Conversations
Yukoh WAKABAYASHI, Masato NAKAYAMA, Takanobu NISHIURA, Yoichi YAMASHITA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Source number plays an important role in blind source separation (BSS) and sound source localization (SSL) based on subspace approach and is used in order to determined the number of separation signals in BSS and the dimension of the signal subspace in SSL. In these fields, it is assumed that source number is given. However, it is impossible to know the number in natural conversations. Recently attention is focused on multi-modal signal processing. Integration between signals received by different sensors, for example an acoustic signal and an image signal, enables to simplify a difficult problem and to improve the performance of the signal processing, compared with single signal processing. This paper proposes multi-modal source number estimation in multi-party conversations by using acoustic and image information. Experiments shows the proposed method outperforms the conventional method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Source Number Estimation / MUSIC Method / Multi-modal Signal Processing / Multi-party Conversations
Paper # EA2014-120,SIP2014-161,SP2014-183
Date of Issue

Conference Information
Committee EA
Conference Date 2015/2/23(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Engineering Acoustics (EA)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Multi-modal Source Number Estimation in Multi-party Conversations
Sub Title (in English)
Keyword(1) Source Number Estimation
Keyword(2) MUSIC Method
Keyword(3) Multi-modal Signal Processing
Keyword(4) Multi-party Conversations
1st Author's Name Yukoh WAKABAYASHI
1st Author's Affiliation Graduate School of Information Science and Engineering, Ritsumeikan University()
2nd Author's Name Masato NAKAYAMA
2nd Author's Affiliation College of Information Science and Engineering, Ritsumeikan University
3rd Author's Name Takanobu NISHIURA
3rd Author's Affiliation College of Information Science and Engineering, Ritsumeikan University
4th Author's Name Yoichi YAMASHITA
4th Author's Affiliation College of Information Science and Engineering, Ritsumeikan University
Date 2015-03-03
Paper # EA2014-120,SIP2014-161,SP2014-183
Volume (vol) vol.114
Number (no) 473
Page pp.pp.-
#Pages 6
Date of Issue