Maximum likelihood based multi-channel isotropic reverberation reduction for hearing aids

Adam Kuklasiński, Simon Doclo, Søren Holdt Jensen, Jesper Jensen

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

26 Citationer (Scopus)

Resumé

We propose a multi-channel Wiener filter for speech dereverberation in hearing aids. The proposed algorithm uses joint maximum likelihood estimation of the speech and late reverberation spectral variances, under the assumption that the late reverberant sound field is cylindrically isotropic. The dereverberation performance of the algorithm is evaluated using computer simulations with realistic hearing aid microphone signals including head-related effects. The algorithm is shown to work well with signals reverberated both by synthetic and by measured room impulse responses, achieving improvements in the order of 0.5 PESQ points and 5 dB frequency-weighted segmental SNR.
OriginalsprogEngelsk
TitelSignal Processing Conference (EUSIPCO), 2014 Proceedings of the 22nd European
Antal sider5
ForlagIEEE Press
Publikationsdato2014
Sider61-65
ISBN (Trykt)978-0-9928626-1-9
StatusUdgivet - 2014
Begivenhed22nd European Signal Processing Conference - Lisbon, Portugal
Varighed: 1 sep. 20145 sep. 2014

Konference

Konference22nd European Signal Processing Conference
LandPortugal
ByLisbon
Periode01/09/201405/09/2014
NavnProceedings of the European Signal Processing Conference
ISSN2076-1465

Fingerprint

Hearing aids
Reverberation
Maximum likelihood
Maximum likelihood estimation
Acoustic fields
Microphones
Impulse response
Computer simulation

Citer dette

Kuklasiński, A., Doclo, S., Jensen, S. H., & Jensen, J. (2014). Maximum likelihood based multi-channel isotropic reverberation reduction for hearing aids. I Signal Processing Conference (EUSIPCO), 2014 Proceedings of the 22nd European (s. 61-65). IEEE Press. Proceedings of the European Signal Processing Conference
Kuklasiński, Adam ; Doclo, Simon ; Jensen, Søren Holdt ; Jensen, Jesper. / Maximum likelihood based multi-channel isotropic reverberation reduction for hearing aids. Signal Processing Conference (EUSIPCO), 2014 Proceedings of the 22nd European. IEEE Press, 2014. s. 61-65 (Proceedings of the European Signal Processing Conference).
@inproceedings{73ebf7ed2faf4daba6868fa47baad91a,
title = "Maximum likelihood based multi-channel isotropic reverberation reduction for hearing aids",
abstract = "We propose a multi-channel Wiener filter for speech dereverberation in hearing aids. The proposed algorithm uses joint maximum likelihood estimation of the speech and late reverberation spectral variances, under the assumption that the late reverberant sound field is cylindrically isotropic. The dereverberation performance of the algorithm is evaluated using computer simulations with realistic hearing aid microphone signals including head-related effects. The algorithm is shown to work well with signals reverberated both by synthetic and by measured room impulse responses, achieving improvements in the order of 0.5 PESQ points and 5 dB frequency-weighted segmental SNR.",
author = "Adam Kuklasiński and Simon Doclo and Jensen, {S{\o}ren Holdt} and Jesper Jensen",
year = "2014",
language = "English",
isbn = "978-0-9928626-1-9",
series = "Proceedings of the European Signal Processing Conference",
publisher = "IEEE Press",
pages = "61--65",
booktitle = "Signal Processing Conference (EUSIPCO), 2014 Proceedings of the 22nd European",

}

Kuklasiński, A, Doclo, S, Jensen, SH & Jensen, J 2014, Maximum likelihood based multi-channel isotropic reverberation reduction for hearing aids. i Signal Processing Conference (EUSIPCO), 2014 Proceedings of the 22nd European. IEEE Press, Proceedings of the European Signal Processing Conference, s. 61-65, Lisbon, Portugal, 01/09/2014.

Maximum likelihood based multi-channel isotropic reverberation reduction for hearing aids. / Kuklasiński, Adam; Doclo, Simon; Jensen, Søren Holdt; Jensen, Jesper.

Signal Processing Conference (EUSIPCO), 2014 Proceedings of the 22nd European. IEEE Press, 2014. s. 61-65 (Proceedings of the European Signal Processing Conference).

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

TY - GEN

T1 - Maximum likelihood based multi-channel isotropic reverberation reduction for hearing aids

AU - Kuklasiński, Adam

AU - Doclo, Simon

AU - Jensen, Søren Holdt

AU - Jensen, Jesper

PY - 2014

Y1 - 2014

N2 - We propose a multi-channel Wiener filter for speech dereverberation in hearing aids. The proposed algorithm uses joint maximum likelihood estimation of the speech and late reverberation spectral variances, under the assumption that the late reverberant sound field is cylindrically isotropic. The dereverberation performance of the algorithm is evaluated using computer simulations with realistic hearing aid microphone signals including head-related effects. The algorithm is shown to work well with signals reverberated both by synthetic and by measured room impulse responses, achieving improvements in the order of 0.5 PESQ points and 5 dB frequency-weighted segmental SNR.

AB - We propose a multi-channel Wiener filter for speech dereverberation in hearing aids. The proposed algorithm uses joint maximum likelihood estimation of the speech and late reverberation spectral variances, under the assumption that the late reverberant sound field is cylindrically isotropic. The dereverberation performance of the algorithm is evaluated using computer simulations with realistic hearing aid microphone signals including head-related effects. The algorithm is shown to work well with signals reverberated both by synthetic and by measured room impulse responses, achieving improvements in the order of 0.5 PESQ points and 5 dB frequency-weighted segmental SNR.

M3 - Article in proceeding

SN - 978-0-9928626-1-9

T3 - Proceedings of the European Signal Processing Conference

SP - 61

EP - 65

BT - Signal Processing Conference (EUSIPCO), 2014 Proceedings of the 22nd European

PB - IEEE Press

ER -

Kuklasiński A, Doclo S, Jensen SH, Jensen J. Maximum likelihood based multi-channel isotropic reverberation reduction for hearing aids. I Signal Processing Conference (EUSIPCO), 2014 Proceedings of the 22nd European. IEEE Press. 2014. s. 61-65. (Proceedings of the European Signal Processing Conference).