Abstrakt
Humans tend to change their way of speaking when they are immersed in a noisy environment, a reflex known as Lombard effect. Current speech enhancement systems based on deep learning do not usually take into account this change in the speaking style, because they are trained with neutral (non-Lombard) speech utterances recorded under quiet conditions to which noise is artificially added. In this paper, we investigate the effects that the Lombard reflex has on the performance of audio-visual speech enhancement systems based on deep learning. The results show that a gap in the performance of as much as approximately 5 dB between the systems trained on neutral speech and the ones trained on Lombard speech exists. This indicates the benefit of taking into account the mismatch between neutral and Lombard speech in the design of audio-visual speech enhancement systems.
Originalsprog | Engelsk |
---|---|
Titel | ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) |
Antal sider | 5 |
Forlag | IEEE |
Publikationsdato | 17 apr. 2019 |
Sider | 6615-6619 |
Artikelnummer | 8682713 |
ISBN (Trykt) | 978-1-4799-8132-8 |
ISBN (Elektronisk) | 978-1-4799-8131-1 |
DOI | |
Status | Udgivet - 17 apr. 2019 |
Begivenhed | 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) - Brighton, Storbritannien Varighed: 12 maj 2019 → 17 maj 2019 https://2019.ieeeicassp.org/ |
Konference
Konference | 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) |
---|---|
Land | Storbritannien |
By | Brighton |
Periode | 12/05/2019 → 17/05/2019 |
Internetadresse |
Navn | I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings |
---|---|
ISSN | 1520-6149 |