Monaural Speech Enhancement using Deep Neural Networks by Maximizing a Short-Time Objective Intelligibility Measure

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

19 Citationer (Scopus)

Abstrakt

In this paper we propose a Deep Neural Network (D NN) based Speech Enhancement (SE) system that is designed to maximize an approximation of the Short-Time Objective Intelligibility (STOI) measure. We formalize an approximate-STOI cost function and derive analytical expressions for the gradients required for DNN training and show that these gradients have desirable properties when used together with gradient based optimization techniques. We show through simulation experiments that the proposed SE system achieves large improvements in estimated speech intelligibility, when tested on matched and unmatched natural noise types, at multiple signal-to-noise ratios. Furthermore, we show that the SE system, when trained using an approximate-STOI cost function performs on par with a system trained with a mean square error cost applied to short-time temporal envelopes. Finally, we show that the proposed SE system performs on par with a traditional DNN based Short- Time Spectral Amplitude (STSA) SE system in terms of estimated speech intelligibility. These results are important because they suggest that traditional DNN based STSA SE systems might be optimal in terms of estimated speech intelligibility.

OriginalsprogEngelsk
Titel2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings
Antal sider5
ForlagIEEE
Publikationsdato2018
Sider5059-5063
Artikelnummer8462040
ISBN (Trykt)9781538646588
ISBN (Elektronisk)978-1-5386-4658-8
DOI
StatusUdgivet - 2018
Begivenhed2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) - Calgary, Canada
Varighed: 15 apr. 201820 apr. 2018
https://2018.ieeeicassp.org/

Konference

Konference2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
LandCanada
ByCalgary
Periode15/04/201820/04/2018
Internetadresse
NavnI E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings
ISSN1520-6149

Fingeraftryk Dyk ned i forskningsemnerne om 'Monaural Speech Enhancement using Deep Neural Networks by Maximizing a Short-Time Objective Intelligibility Measure'. Sammen danner de et unikt fingeraftryk.

  • Citationsformater

    Kolbæk, M., Tan, Z-H., & Jensen, J. (2018). Monaural Speech Enhancement using Deep Neural Networks by Maximizing a Short-Time Objective Intelligibility Measure. I 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings (s. 5059-5063). [8462040] IEEE. I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings https://doi.org/10.1109/ICASSP.2018.8462040