音声と騒音の密度比推定を用いた音声区間検出法

カテゴリ: 論文誌(論文単位)

グループ名: 【C】電子・情報・システム部門

発行日: 2013/08/01

タイトル(英語): Voice Activity Detection Using Density Ratio Estimation of Speech and Noise

著者名: 太刀岡　勇気（三菱電機 (株) 情報技術総合研究所），花沢　利行（三菱電機 (株) 情報技術総合研究所），成田　知宏（三菱電機 (株) 情報技術総合研究所），石井　純（三菱電機 (株) 情報技術総合研究所）

著者名(英語): Yuuki Tachioka (Information Technology R&D Center, Mitsubishi Electric Corporation), Toshiyuki Hanazawa (Information Technology R&D Center, Mitsubishi Electric Corporation), Tomohiro Narita (Information Technology R&D Center, Mitsubishi Electric Corporation), Jun Ishii (Information Technology R&D Center, Mitsubishi Electric Corporation)

キーワード: 音声区間検出，尤度比検定，密度比推定，耐騒音性，判別分析による閾値の決定　　Voice activity detection，Likelihood ratio test，Density ratio estimation，Noise robustness，Threshold determination by discriminant analysis

要約(英語): In this paper, we propose a robust voice activity detection (VAD) method that uses a density ratio model. For VAD under highly noisy environments, the likelihood ratio test (LRT) is effective. Conventional LRT constructs speech and noise models, calculates the likelihood of each model, and takes the ratio of those likelihoods to detect speech. Although some improved LRT have been proposed, in conventional LRT, it has not been taken into account that the likelihood ratio of speech and noise model is required, not the likelihood of each model. The proposed method directly estimates the likelihood ratio without calculating each likelihood using an density ratio model obtained in advance by density ratio estimation procedure. Moreover, there is the problem of determining thresholds, which are used for VAD and significantly affect its performance. We propose a method that automatically determines thresholds using discriminant analysis. The experiments show that the proposed method is more effective than conventional methods especially under non-stationary noisy environments.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.133 No.8 （2013） 特集：パワー半導体光源とその応用技術

本誌掲載ページ: 1549-1555 p

原稿種別: 論文／日本語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejeiss/133/8/133_1549/_article/-char/ja/