Deep clustering: Discriminative embeddings for segmentation and separation

John R. Hershey, Zhuo Chen, Jonathan Le Roux, Shinji Watanabe

研究成果: Conference contribution

501 被引用数 (Scopus)

抄録

We address the problem of «cocktail-party» source separation in a deep learning framework called deep clustering. Previous deep network approaches to separation have shown promising performance in scenarios with a fixed number of sources, each belonging to a distinct signal class, such as speech and noise. However, for arbitrary source classes and number, «class-based» methods are not suitable. Instead, we train a deep network to assign contrastive embedding vectors to each time-frequency region of the spectrogram in order to implicitly predict the segmentation labels of the target spectrogram from the input mixtures. This yields a deep network-based analogue to spectral clustering, in that the embeddings form a low-rank pair-wise affinity matrix that approximates the ideal affinity matrix, while enabling much faster performance. At test time, the clustering step «decodes» the segmentation implicit in the embeddings by optimizing K-means with respect to the unknown assignments. Preliminary experiments on single-channel mixtures from multiple speakers show that a speaker-independent model trained on two-speaker mixtures can improve signal quality for mixtures of held-out speakers by an average of 6dB. More dramatically, the same model does surprisingly well with three-speaker mixtures.

本文言語English
ホスト出版物のタイトル2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings
出版社Institute of Electrical and Electronics Engineers Inc.
ページ31-35
ページ数5
2016-May
ISBN(電子版)9781479999880
DOI
出版ステータスPublished - 2016 5 18
外部発表はい
イベント41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Shanghai, China
継続期間: 2016 3 202016 3 25

Other

Other41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016
国/地域China
CityShanghai
Period16/3/2016/3/25

ASJC Scopus subject areas

  • 信号処理
  • ソフトウェア
  • 電子工学および電気工学

フィンガープリント

「Deep clustering: Discriminative embeddings for segmentation and 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