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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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.

Original languageEnglish
Title of host publication2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2020 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages858-862
Number of pages5
ISBN (Electronic)9789881476883
Publication statusPublished - 2020 Dec 7
Externally publishedYes
Event2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2020 - Virtual, Auckland, New Zealand
Duration: 2020 Dec 72020 Dec 10

Publication series

Name2020 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
Country/TerritoryNew Zealand
CityVirtual, Auckland
Period20/12/720/12/10

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Hardware and Architecture
  • Signal Processing
  • Decision Sciences (miscellaneous)
  • Instrumentation

Fingerprint

Dive into the research topics of 'Study on Geometrically Constrained IVA with Auxiliary Function Approach and VCD for In-Car Communication'. Together they form a unique fingerprint.

Cite this