Speech enhancement using bayesianwavenet

Kaizhi Qian, Yang Zhang, Shiyu Chang, Xuesong Yang, Dinei Florèncio, Mark Hasegawa-Johnson

Research output: Contribution to journalConference articlepeer-review


In recent years, deep learning has achieved great success in speech enhancement. However, there are two major limitations regarding existing works. First, the Bayesian framework is not adopted in many such deep-learning-based algorithms. In particular, the prior distribution for speech in the Bayesian framework has been shown useful by regularizing the output to be in the speech space, and thus improving the performance. Second, the majority of the existing methods operate on the frequency domain of the noisy speech, such as spectrogram and its variations. The clean speech is then reconstructed using the approach of overlap-Add, which is limited by its inherent performance upper bound. This paper presents a Bayesian speech enhancement framework, called BaWN (Bayesian WaveNet), which directly operates on raw audio samples. It adopts the recently announced WaveNet, which is shown to be effective in modeling conditional distributions of speech samples while generating natural speech. Experiments show that BaWN is able to recover clean and natural speech.

Original languageEnglish (US)
Pages (from-to)2013-2017
Number of pages5
JournalProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
StatePublished - 2017
Event18th Annual Conference of the International Speech Communication Association, INTERSPEECH 2017 - Stockholm, Sweden
Duration: Aug 20 2017Aug 24 2017


  • Bayesian Framework
  • Convolutional Neural Network
  • Model-Based
  • Speech Enhancement
  • Wavenet

ASJC Scopus subject areas

  • Language and Linguistics
  • Human-Computer Interaction
  • Signal Processing
  • Software
  • Modeling and Simulation


Dive into the research topics of 'Speech enhancement using bayesianwavenet'. Together they form a unique fingerprint.

Cite this