Study on Geometrically Constrained IVA with Auxiliary Function Approach and VCD for In-Car Communication

Kana Goto, Li Li, Riki Takahashi, Shoji Makino, Takeshi Yamada

研究成果: Conference contribution

抄録

In this paper, we apply a geometrically constrained independent vector analysis (GCIVA) method to an in-car speech enhancement system and confirm its effectiveness in realistic environments. Specifically, we employ GCIVA with the auxiliary function approach and vectorwise coordinate descent (GCAVIVA) to enhance the target speech in in-car communication, where multiple co-occurring speeches are recorded with a triangle microphone array. GCAV-IVA is a recently proposed geometrically constrained blind source separation method, that has been shown to be powerful in directional speech enhancement with a limited number of microphones. Moreover, it is noteworthy for its fast convergence, low computational cost, and non requirement of step-size tuning, which makes it suitable for practical applications. However, the experiments using this method were only conducted using simulated impulse responses (IRs). In this study we investigates GCAV-IVA using measured in-car IRs to simulate more realistic environments. Moreover, we apply GCAV-IVA in a data-adaptive manner. The experimental results revealed that GCAV-IVA significantly outperformed conventional beamforming methods in terms of signal-to-distortion ratio.

本文言語English
ホスト出版物のタイトル2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2020 - Proceedings
出版社Institute of Electrical and Electronics Engineers Inc.
ページ858-862
ページ数5
ISBN(電子版)9789881476883
出版ステータスPublished - 2020 12 7
外部発表はい
イベント2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2020 - Virtual, Auckland, New Zealand
継続期間: 2020 12 72020 12 10

出版物シリーズ

名前2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2020 - Proceedings

Conference

Conference2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2020
国/地域New Zealand
CityVirtual, Auckland
Period20/12/720/12/10

ASJC Scopus subject areas

  • 人工知能
  • コンピュータ ネットワークおよび通信
  • コンピュータ ビジョンおよびパターン認識
  • ハードウェアとアーキテクチャ
  • 信号処理
  • 決定科学(その他)
  • 器械工学

フィンガープリント

「Study on Geometrically Constrained IVA with Auxiliary Function Approach and VCD for In-Car Communication」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