Efficient and stable adversarial learning using unpaired data for unsupervised multichannel speech separation

Yu Nakagome*, Masahito Togami, Tetsuji Ogawa, Tetsunori Kobayashi

*この研究の対応する著者

研究成果: Conference contribution

抄録

This study presents a framework to enable efficient and stable adversarial learning of unsupervised multichannel source separation models. When the paired data, i.e., the mixture and the corresponding clean speech, are not available for training, it is promising to exploit generative adversarial networks (GANs), where a source separation system is treated as a generator and trained to bring the distribution of the separated (fake) speech closer to that of the clean (real) speech. The separated speech, however, contains many errors, especially when the system is trained unsupervised and can be easily distinguished from the clean speech. A real/fake binary discriminator therefore will stop the adversarial learning process unreasonably early. This study aims to balance the convergence of the generator and discriminator to achieve efficient and stable learning. For that purpose, the autoencoder-based discriminator and more stable adversarial loss, which are designed in boundary equilibrium GAN (BEGAN), are introduced. In addition, generator-specific distortions are added to real examples so that the models can be trained to focus only on source separation. Experimental comparisons demonstrated that the present stabilizing learning techniques improved the performance of multiple unsupervised source separation systems.

本文言語English
ホスト出版物のタイトル22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021
出版社International Speech Communication Association
ページ2323-2327
ページ数5
ISBN(電子版)9781713836902
DOI
出版ステータスPublished - 2021
イベント22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021 - Brno, Czech Republic
継続期間: 2021 8 302021 9 3

出版物シリーズ

名前Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
3
ISSN(印刷版)2308-457X
ISSN(電子版)1990-9772

Conference

Conference22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021
国/地域Czech Republic
CityBrno
Period21/8/3021/9/3

ASJC Scopus subject areas

  • 言語および言語学
  • 人間とコンピュータの相互作用
  • 信号処理
  • ソフトウェア
  • モデリングとシミュレーション

フィンガープリント

「Efficient and stable adversarial learning using unpaired data for unsupervised multichannel speech separation」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