Determined audio source separation with multichannel star generative adversarial network

Li Li, Hirokazu Kameoka, Shoji Makino

研究成果: Conference contribution

9 被引用数 (Scopus)

抄録

This paper proposes a multichannel source separation approach, which uses a star generative adversarial network (StarGAN) to model power spectrograms of sources. Various studies have shown the significant contributions of a precise source model to the performance improvement in audio source separation, which indicates the importance of developing a better source model. In this paper, we explore the potential of StarGAN for modeling source spectrograms and investigate the effectiveness of the StarGAN source model in determined multichannel source separation by incorporating it into a frequency-domain independent component analysis (ICA) framework. The experimental results reveal that the proposed StarGAN-based method outperformed conventional methods that use non-negative matrix factorization (NMF) or a variational autoencoder (VAE) for source spectrogram modeling.

本文言語English
ホスト出版物のタイトルProceedings of the 2020 IEEE 30th International Workshop on Machine Learning for Signal Processing, MLSP 2020
出版社IEEE Computer Society
ISBN(電子版)9781728166629
DOI
出版ステータスPublished - 2020 9月
外部発表はい
イベント30th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2020 - Virtual, Espoo, Finland
継続期間: 2020 9月 212020 9月 24

出版物シリーズ

名前IEEE International Workshop on Machine Learning for Signal Processing, MLSP
2020-September
ISSN(印刷版)2161-0363
ISSN(電子版)2161-0371

Conference

Conference30th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2020
国/地域Finland
CityVirtual, Espoo
Period20/9/2120/9/24

ASJC Scopus subject areas

  • 人間とコンピュータの相互作用
  • 信号処理

フィンガープリント

「Determined audio source separation with multichannel star generative adversarial network」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