Least Squares Estimate of the Initial Phases in STFT based Speech Enhancement

Sidsel Marie Nørholm, Martin Krawczyk-Becker, Timo Gerkmann, Steven van de Par, Jesper Rindom Jensen, Mads Græsbøll Christensen

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

1 Citation (Scopus)
243 Downloads (Pure)

Abstract

In this paper, we consider single-channel speech enhancement in the short time Fourier transform (STFT) domain. We suggest to improve an STFT phase estimate by estimating the initial phases. The method is based on the harmonic model and a model for the phase evolution over time. The initial phases are estimated by setting up a least squares problem between the noisy phase and the model for phase evolution. Simulations on synthetic and speech signals show a decreased error on the phase when an estimate of the initial phase is included compared to using the noisy phase as an initialisation. The error on the phase is decreased at input SNRs from -10 to 10 dB. Reconstructing the signal using the clean amplitude, the mean squared error is decreased and the PESQ score is increased.
Original languageEnglish
Title of host publicationINTERSPEECH 2015 : 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, September 6-10, 2015
PublisherInternational Speech Communications Association
Publication date2015
Pages1750-1754
Publication statusPublished - 2015
EventINTERSPEECH 2015 16th Annual Conference of the International Speech Communication Association - Dresden, Germany
Duration: 6 Sept 201510 Sept 2015

Conference

ConferenceINTERSPEECH 2015 16th Annual Conference of the International Speech Communication Association
Country/TerritoryGermany
CityDresden
Period06/09/201510/09/2015
SeriesINTERSPEECH
ISSN1990-9770

Fingerprint

Dive into the research topics of 'Least Squares Estimate of the Initial Phases in STFT based Speech Enhancement'. Together they form a unique fingerprint.

Cite this