A single channel speech enhancement approach by combining statistical criterion and Multi-frame Sparse Dictionary Learning

Hung Wei Tseng, Srikanth Vishnubhotla, Mingyi Hong, Xiangfeng Wang, Jinjun Xiao

Research output: Contribution to journalConference articlepeer-review

2 Scopus citations

Abstract

In this paper, we consider the single-channel speech enhancement problem, in which a clean speech signal needs to be estimated from a noisy observation. To capture the characteristics of both the noise and speech signals, we combine the well-known Short-Time-Spectrum-Amplitude (STSA) estimator with a machine learning based technique called Multi-frame Sparse Dictionary Learning (MSDL). The former utilizes statistical information for denoising, while the latter helps better preserve speech, especially its temporal structure. The proposed algorithm, named STSA-MSDL, outperforms standard statistical algorithms such as the Wiener filter, STSA estimator, as well as dictionary based algorithms when applied to the TIMIT database, using four different objective metrics that measure speech intelligibility, speech distortion, background noise reduction, and the overall quality.

Original languageEnglish (US)
Pages (from-to)451-455
Number of pages5
JournalProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
StatePublished - Jan 1 2013
Event14th Annual Conference of the International Speech Communication Association, INTERSPEECH 2013 - Lyon, France
Duration: Aug 25 2013Aug 29 2013

Keywords

  • ADMM
  • Contextual effects
  • Dictionary learning
  • STSA
  • Speech enhancement

Fingerprint Dive into the research topics of 'A single channel speech enhancement approach by combining statistical criterion and Multi-frame Sparse Dictionary Learning'. Together they form a unique fingerprint.

Cite this