Presentation 2014-11-17
Unified approach for auditory scene analysis based on multichannel factorial hidden Markov model
Takuya HIGUCHI, Hirokazu KAMEOKA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper deals with the problems of audio source separation, audio event detection, dereverberation and DOA estimation. We focus on the fact that these problems are interdependent, and propose an unified approach for these problem. We model the generative process of observed signals with parameters each of which corresponds to a specific aspect of an audio source. Through the parameter inference, We can simultaneously salve the problems of auditory scene analysis.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Non-negative matrix factorization / blind source separation / dereverberation / audio event detection / DOA
Paper # IBISML2014-57
Date of Issue

Conference Information
Committee IBISML
Conference Date 2014/11/10(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 Information-Based Induction Sciences and Machine Learning (IBISML)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Unified approach for auditory scene analysis based on multichannel factorial hidden Markov model
Sub Title (in English)
Keyword(1) Non-negative matrix factorization
Keyword(2) blind source separation
Keyword(3) dereverberation
Keyword(4) audio event detection
Keyword(5) DOA
1st Author's Name Takuya HIGUCHI
1st Author's Affiliation Graduate School of Information Science and Technology, The University of Tokyo()
2nd Author's Name Hirokazu KAMEOKA
2nd Author's Affiliation Graduate School of Information Science and Technology, The University of Tokyo:NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation
Date 2014-11-17
Paper # IBISML2014-57
Volume (vol) vol.114
Number (no) 306
Page pp.pp.-
#Pages 8
Date of Issue