Improved expectation-maximization framework for speech enhancement based on iterative noise estimation

Tingtian Li, Pak Kong Lun, Tak Wai Shen

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

1 Citation (Scopus)

Abstract

Recently, our team developed a novel Expectation Maximization (EM) framework for speech enhancement. It gives a significantly improved estimation of the speech power spectrum that outperforms many traditional approaches. In this paper, we further extend the EM framework by including an efficient iterative noise estimation algorithm, which improves the estimation of the noise power spectrum from the noisy observation. Besides, we notice that some speech frames, particularly those with high signal to noise ratio (SNR), need to be monitored closely during the iterative enhancement process, or spectral distortion may result. A stopping criterion is thus developed to stop the iteration when a good result has been achieved. Experimental results show that the new approach gives a significant improvement over the original EM framework and also traditional speech enhancement methods.
Original languageEnglish
Title of host publication2015 IEEE International Conference on Digital Signal Processing, DSP 2015
PublisherIEEE
Pages287-291
Number of pages5
Volume2015-September
ISBN (Electronic)9781479980581
DOIs
Publication statusPublished - 9 Sept 2015
EventIEEE International Conference on Digital Signal Processing, DSP 2015 - Singapore, Singapore
Duration: 21 Jul 201524 Jul 2015

Conference

ConferenceIEEE International Conference on Digital Signal Processing, DSP 2015
Country/TerritorySingapore
CitySingapore
Period21/07/1524/07/15

Keywords

  • EM algorithm
  • iterative regularization
  • noise power spectral density estimation
  • Speech enhancement

ASJC Scopus subject areas

  • Signal Processing

Fingerprint

Dive into the research topics of 'Improved expectation-maximization framework for speech enhancement based on iterative noise estimation'. Together they form a unique fingerprint.

Cite this