Joint separation, dereverberation and classification of multiple sources using multichannel variational autoencoder with auxiliary classifier

Shota Inoue, Hirokazu Kameoka, Li Li, Shoji Makino

研究成果: Conference contribution

抄録

This paper proposes a unified approach to jointly solving the separation, dereverberation, and classification of mixed sound sources from microphone array observations. The proposed method uses a frequency-wise convolutive mixture model to express the mixing process under highly reverberant environments and the auxiliary classifier conditional variational autoencoder (ACVAE) to model the complex spectrograms of underlying sources. Using an ACVAE as the source generative model allows us to estimate the latent vectors and the class index of each source in a test mixture by computing the outputs of the pretrained approximate posterior inference networks without using backpropagation. We experimentally confirmed that the proposed method outperformed conventional methods in terms of both computation time and source classification.

本文言語English
ホスト出版物のタイトルProceedings of the 23rd International Congress on Acoustics
ホスト出版物のサブタイトルIntegrating 4th EAA Euroregio 2019
編集者Martin Ochmann, Vorlander Michael, Janina Fels
出版社International Commission for Acoustics (ICA)
ページ6953-6960
ページ数8
ISBN(電子版)9783939296157
DOI
出版ステータスPublished - 2019
外部発表はい
イベント23rd International Congress on Acoustics: Integrating 4th EAA Euroregio, ICA 2019 - Aachen, Germany
継続期間: 2019 9 92019 9 23

出版物シリーズ

名前Proceedings of the International Congress on Acoustics
2019-September
ISSN(印刷版)2226-7808
ISSN(電子版)2415-1599

Conference

Conference23rd International Congress on Acoustics: Integrating 4th EAA Euroregio, ICA 2019
国/地域Germany
CityAachen
Period19/9/919/9/23

ASJC Scopus subject areas

  • 機械工学
  • 音響学および超音波学

フィンガープリント

「Joint separation, dereverberation and classification of multiple sources using multichannel variational autoencoder with auxiliary classifier」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