Ensemble integration of calibrated speaker localization and statistical speech detection in domestic environments

Yuuki Tachioka, Tomohiro Narita, Shinji Watanabe, Jonathan Le Roux

研究成果: Conference contribution

7 被引用数 (Scopus)

抄録

This paper describes speaker localization and speech detection techniques for domestic environments. In real environments, it is hard to localize speakers because reverberation causes discrepancy from the simple spherical wave assumption. We propose a template-based method that calibrates the localization errors included in conventional methods. In addition, we use statistical speech detection methods to deal with noises. However, in this challenge, there are five rooms and leaked utterances from other rooms must be rejected. This kind of rejection is hard to perform by only using speech detection results. To address this problem, we also propose a method that integrates speech localization and speech detection using a minimum cost criterion or a classifier-based strategy. The proposed method achieved an accuracy of 0.712 for speaker localization and an F value of 0.743 for speech detection on the development set compared with the baseline 0.559 and 0.570, and 0.666 and 0.706 on the test set compared with the baseline 0.517 and 0.602.

本文言語English
ホスト出版物のタイトル2014 4th Joint Workshop on Hands-Free Speech Communication and Microphone Arrays, HSCMA 2014
出版社IEEE Computer Society
ページ162-166
ページ数5
ISBN(印刷版)9781479931095
DOI
出版ステータスPublished - 2014 1 1
外部発表はい
イベント2014 4th Joint Workshop on Hands-Free Speech Communication and Microphone Arrays, HSCMA 2014 - Villers-les-Nancy, France
継続期間: 2014 5 122014 5 14

出版物シリーズ

名前2014 4th Joint Workshop on Hands-Free Speech Communication and Microphone Arrays, HSCMA 2014

Other

Other2014 4th Joint Workshop on Hands-Free Speech Communication and Microphone Arrays, HSCMA 2014
CountryFrance
CityVillers-les-Nancy
Period14/5/1214/5/14

ASJC Scopus subject areas

  • Computer Networks and Communications

フィンガープリント 「Ensemble integration of calibrated speaker localization and statistical speech detection in domestic environments」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル