Model based Estimation of STP parameters for Binaural Speech Enhancement

Mathew Shaji Kavalekalam, Jesper Kjær Nielsen, Mads Græsbøll Christensen, Jesper Bünsow Boldt

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

180 Downloads (Pure)

Abstract

This paper deals with the estimation of the short-term predictor (STP) parameters of speech and noise in a binaural framework. A binaural model based approach is proposed for estimating the power spectral density (PSD) of speech and noise at the individual ears for an arbitrary position of the speech source. The estimated PSDs can be subsequently used for enhancement in a binaural framework. The experimental results show that taking into account the position of the speech source using the proposed method leads to improved modelling and enhancement of the noisy speech.
OriginalsprogEngelsk
Titel2018 26th European Signal Processing Conference (EUSIPCO)
ForlagIEEE
Publikationsdato2018
Artikelnummer8553145
ISBN (Trykt)978-90-827970-0-8, 978-1-5386-3736-4
ISBN (Elektronisk)978-9-0827-9701-5
DOI
StatusUdgivet - 2018
Begivenhed26th European Signal Processing Conference (EUSIPCO 2018) - Rome, Italien
Varighed: 3 sep. 20187 sep. 2018
Konferencens nummer: 26
http://www.eusipco2018.org

Konference

Konference26th European Signal Processing Conference (EUSIPCO 2018)
Nummer26
Land/OmrådeItalien
ByRome
Periode03/09/201807/09/2018
Internetadresse
NavnProceedings of the European Signal Processing Conference
ISSN2076-1465

Fingeraftryk

Dyk ned i forskningsemnerne om 'Model based Estimation of STP parameters for Binaural Speech Enhancement'. Sammen danner de et unikt fingeraftryk.

Citationsformater