Abstract
The reverberation of an acoustic channel can be characterised by two frequency-dependent parameters: the reverberation time and the direct-to-reverberant energy ratio. This paper presents an algorithm for blindly determining these parameters from a single-channel speech signal. The algorithm uses an extended Kalman filter to estimate the parameters together with a hidden semi-Markov model to identify intervals of speech activity.
Originalsprog | Engelsk |
---|---|
Titel | IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2015 |
Forlag | IEEE Signal Processing Society |
Publikationsdato | 2015 |
Sider | 31 - 35 |
ISBN (Elektronisk) | 978-1-4673-6997-8 |
DOI | |
Status | Udgivet - 2015 |
Begivenhed | 40th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2015 - Brisbane, Australien Varighed: 19 apr. 2015 → 24 apr. 2015 Konferencens nummer: 2015 |
Konference
Konference | 40th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2015 |
---|---|
Nummer | 2015 |
Land/Område | Australien |
By | Brisbane |
Periode | 19/04/2015 → 24/04/2015 |
Navn | I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings |
---|---|
ISSN | 1520-6149 |