Presentation 2014-02-28
A proposal of close/distant talker discrimination based on kurtosis of linear prediction residual signals
Kohei HAYASHIDA, Masato NAKAYAMA, Takanobu NISHIURA, Yoichi YAMASHITA, Toshiharu HORIUCHI, Tsuneo KATO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Desired/undesired speech discrimination is as important as speech/non-speech discrimination to achieve useful applications such as speech interfaces and teleconferencing systems. Conventional methods of voice activity detection utilize the directional information of sound sources to distinguish desired from undesired speech and have to utilize multiple microphones. Here, we assumed that the desired talkers would be close to the microphone, and we proposed a new method to discriminate close-talking speech from distant-talking speech with a single microphone based on the kurtosis of the linear prediction residual signals. The experimental results revealed that the proposed method could distinguish close-talking speech from distant-talking speech within a 10% equal error rate in ordinary reverberant environments with real-time processing.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Close/distant talker discrimination / linear prediction residual signal / kurtosis
Paper # SP2013-107
Date of Issue

Conference Information
Committee SP
Conference Date 2014/2/21(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 Speech (SP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A proposal of close/distant talker discrimination based on kurtosis of linear prediction residual signals
Sub Title (in English)
Keyword(1) Close/distant talker discrimination
Keyword(2) linear prediction residual signal
Keyword(3) kurtosis
1st Author's Name Kohei HAYASHIDA
1st Author's Affiliation Graduate School of Information Scinence and Engineering, Ritsumeikan University()
2nd Author's Name Masato NAKAYAMA
2nd Author's Affiliation Colleage of Information Science and Engineering, Ritsumeikan University
3rd Author's Name Takanobu NISHIURA
3rd Author's Affiliation Colleage of Information Science and Engineering, Ritsumeikan University
4th Author's Name Yoichi YAMASHITA
4th Author's Affiliation Colleage of Information Science and Engineering, Ritsumeikan University
5th Author's Name Toshiharu HORIUCHI
5th Author's Affiliation User Interface Laboratory, KDDI R&D Laboratories, Inc.
6th Author's Name Tsuneo KATO
6th Author's Affiliation User Interface Laboratory, KDDI R&D Laboratories, Inc.
Date 2014-02-28
Paper # SP2013-107
Volume (vol) vol.113
Number (no) 452
Page pp.pp.-
#Pages 6
Date of Issue