An uncertainty decoding approach to noise- and reverberation-robust speech recognition
2013 (English)In: ICASSP IEEE Int Conf Acoust Speech Signal Process Proc, 2013, 7388-7392 p.Conference paper (Refereed)
The generic REMOS (REverberation MOdeling for robust Speech recognition) concept is extended in this contribution to cope with additional noise components. REMOS originally embeds an explicit reverberation model into a hiddenMarkov model (HMM) leading to a relaxed conditional independence assumption for the observed feature vectors. During recognition, a nonlinear optimization problem is to be solved in order to adapt the HMMs' output probability density functions to the current reverberation conditions. The extension for additional noise components necessitates a modified numerical solver for the nonlinear optimization problem. We propose an approximation scheme based on continuous piecewise linear regression. Connected-digit recognition experiments demonstrate the potential of REMOS in reverberant and noisy environments. They furthermore reveal that the benefit of an explicit reverberation model, overcoming the conditional independence assumption, increases with increasing signal-to-noise-ratios.
Place, publisher, year, edition, pages
2013. 7388-7392 p.
, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, ISSN 1520-6149
automatic speech recognition, noise robustness, piecewise linear regression, reverberation robustness, uncertainty decoding
Electrical Engineering, Electronic Engineering, Information Engineering
IdentifiersURN: urn:nbn:se:kth:diva-140040DOI: 10.1109/ICASSP.2013.6639098ScopusID: 2-s2.0-84890473474ISBN: 9781479903566OAI: oai:DiVA.org:kth-140040DiVA: diva2:689556
2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013, 26 May 2013 through 31 May 2013, Vancouver, BC
QC 201401212014-01-212014-01-162014-01-21Bibliographically approved