Phasebook and friends: Leveraging discrete representations for source separation

Jonathan Le Roux*, Gordon Wichern, Shinji Watanabe, Andy Sarroff, John R. Hershey

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

49 Citations (Scopus)


Speech enhancement and source separation systems based on deep learning have recently reached unprecedented levels of quality, to the point that performance is reaching a new ceiling. Most systems rely on estimating the magnitude of a target source by estimating a real-valued mask to be applied to a time-frequency representation of the mixture signal. A limiting factor in such approaches is a lack of phase estimation: the phase of the mixture is most often used when reconstructing the estimated time-domain signal. Here, we propose 'magbook,' 'phasebook,' and 'combook,' three new types of layers based on discrete representations that can be used to estimate complex time-frequency masks. Magbook layers extend classical sigmoidal units and a recently introduced convex softmax activation for mask-based magnitude estimation. Phasebook layers use a similar structure to give an estimate of the phase mask without suffering from phase wrapping issues. Combook layers are an alternative to the magbook-phasebook combination that directly estimate complex masks. We present various training and inference schemes involving these representations, and explain in particular how to include them in an end-to-end learning framework. We also present an oracle study to assess upper bounds on performance for various types of masks using discrete phase representations. We evaluate the proposed methods on the wsj0-2mix dataset, a well-studied corpus for single-channel speaker-independent speaker separation, matching the performance of state-of-the-art mask-based approaches without requiring additional phase reconstruction steps.

Original languageEnglish
Article number8664086
Pages (from-to)370-382
Number of pages13
JournalIEEE Journal on Selected Topics in Signal Processing
Issue number2
Publication statusPublished - 2019 May
Externally publishedYes


  • Source separation
  • deep clustering
  • deep learning
  • discrete representation
  • mask inference
  • phase
  • quantization

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering


Dive into the research topics of 'Phasebook and friends: Leveraging discrete representations for source separation'. Together they form a unique fingerprint.

Cite this