Speaker separation in multi-channel environment using deep learning

• Item type: SIG Technical Reports(1)
• 公開日: 2017-02-10
• タイトル: Speaker separation in multi-channel environment using deep learning
• タイトル / 言語: en
• タイトル: Speaker separation in multi-channel environment using deep learning
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: 音声認識・応用
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_18gh
• 資源タイプ: technical report
• 著者所属: Tokyo Institute of Technology
• 著者所属: Tokyo Institute of Technology
• 著者所属: Tokyo Institute of Technology
• 著者所属(英): en
• 著者所属(英): Tokyo Institute of Technology
• 著者所属(英): en
• 著者所属(英): Tokyo Institute of Technology
• 著者所属(英): en
• 著者所属(英): Tokyo Institute of Technology
• 著者名: Conggui, Liu; Nakamasa, Inoue; Koichi, Shinoda
• 著者名(英): Conggui, Liu; Nakamasa, Inoue; Koichi, Shinoda
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: This paper addresses multi-channel speaker separation based on a deep delay-and-subtraction beamformer. Deep neural network (DNN) is first applied to estimate the delay time between speakers and microphones, and then speakers' speech is recovered from mixed signals by using a delay-and-subtraction algorithm. We evaluated our method by using simulated data made from WSJCAM0 database. The proposed method achieved high precision source localization, and about 62% relative improvement on word error rate (WER) over a delay-and-sum (DS) beamformer.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: This paper addresses multi-channel speaker separation based on a deep delay-and-subtraction beamformer. Deep neural network (DNN) is first applied to estimate the delay time between speakers and microphones, and then speakers' speech is recovered from mixed signals by using a delay-and-subtraction algorithm. We evaluated our method by using simulated data made from WSJCAM0 database. The proposed method achieved high precision source localization, and about 62% relative improvement on word error rate (WER) over a delay-and-sum (DS) beamformer.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AN10442647
• 書誌情報: 研究報告音声言語情報処理（SLP）; 巻 2017-SLP-115, 号 11, p. 1-6, 発行日 2017-02-10
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 2188-8663
• Notice: SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc.
• 出版者 / 言語: ja
• 出版者: 情報処理学会