A General Framework for Multichannel Speech Dereverberation Exploiting Sparsity

Jukic A, van Waterschoot T, Gerkmann T, Doclo S. A General Framework for Multichannel Speech Dereverberation Exploiting Sparsity. In: AES Conference: 60th International Conference: Dereverberation and Reverberation of Audio, Music, and Speech. Audio Engineering Society; 2016. Paper 9-1. Available from: https://aes.org/publications/elibrary-page/?id=18089

@inproceedings{Jukic2016_18089,
  author = {Jukic, Ante and van Waterschoot, Toon and Gerkmann, Timo and Doclo, Simon},
  title = {{A General Framework for Multichannel Speech Dereverberation Exploiting Sparsity}},
  booktitle = {AES Conference: 60th International Conference: Dereverberation and Reverberation of Audio, Music, and Speech},
  note = {Paper 9-1},
  year = {2016},
  month = jan,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=18089}
}

TY  - CPAPER
TI  - A General Framework for Multichannel Speech Dereverberation Exploiting Sparsity
AU  - Jukic, Ante
AU  - van Waterschoot, Toon
AU  - Gerkmann, Timo
AU  - Doclo, Simon
T2  - AES Conference: 60th International Conference: Dereverberation and Reverberation of Audio, Music, and Speech
M1  - Paper 9-1
PY  - 2016
DA  - 2016/01/06
UR  - https://aes.org/publications/elibrary-page/?id=18089
PB  - Audio Engineering Society
LA  - en
AB  - We consider the problem of blind multi-channel speech dereverberation without the knowledge of room acoustics. The dereverberated speech component is estimated by subtracting the undesired component, estimated using multi-channel linear prediction (MCLP), from the reference microphone signal. In this paper we present a framework for MCLP-based speech dereverberation by exploiting sparsity in the time-frequency domain. The presented framework uses a wideband or a narrowband signal model and a sparse analysis or synthesis model for the desired speech component. The proposed problems involving a reweighted $\ell_1$-norm, are solved in a flexible optimization framework. The obtained results are comparable to the state of the art, motivating further extensions exploiting sparsity and speech structure.
ER  -