Presentation 2008/3/15
Voice Activity Interval Detection by Fusing Audio and Lip Vertical Line Image
Tetsuji YAMAGUCHI, Nozomu HAMADA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this study, we propose a VAD estimation method under low signal to noise ratio environment by fusing audio and novel lip vertical line image. First, the proposed technique detects the interval where lips move by using lip vertical line image. Secondly, acoustic signal and its spectrum is used to detect an utterance voice interval. The final utterance interval is decided by combining these two intervals. Finally, the effectiveness of the proposal method is verified through experiments.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Voice Activity Detection / VAD / Multimodal / Lip Vertical Line
Paper # HIP2007-161
Date of Issue

Conference Information
Committee HIP
Conference Date 2008/3/15(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 Human Information Processing (HIP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Voice Activity Interval Detection by Fusing Audio and Lip Vertical Line Image
Sub Title (in English)
Keyword(1) Voice Activity Detection
Keyword(2) VAD
Keyword(3) Multimodal
Keyword(4) Lip Vertical Line
1st Author's Name Tetsuji YAMAGUCHI
1st Author's Affiliation Signal Processing Lab. School of Integrated Design Engineering, Keio University()
2nd Author's Name Nozomu HAMADA
2nd Author's Affiliation Signal Processing Lab. School of Integrated Design Engineering, Keio University
Date 2008/3/15
Paper # HIP2007-161
Volume (vol) vol.107
Number (no) 553
Page pp.pp.-
#Pages 6
Date of Issue