Proceedings Article10.1109/ICASSP.2012.6287935
Robust partial multichannel equalization techniques for speech dereverberation
Ina Kodrasi,Simon Doclo +1 more
- 25 Mar 2012
- pp 537-540
21
TL;DR: Experimental results for speech dereverberation show that the regularized P-MINT method outperforms state-of-the-art techniques such as channel shortening and the relaxed multichannel least-squares method in terms of robustness to channel estimation errors.
read more
Abstract: This paper presents a novel approach for partial multichannel equalization using the multiple-input/output inverse theorem with the first part of one of the estimated channels as the target response (P-MINT). In order to further increase the robustness against channel estimation errors, two extensions are proposed, i.e. the incorporation of a regularization parameter in the inverse filter design and a truncated singular value decomposition approach. Experimental results for speech dereverberation show that the regularized P-MINT method outperforms state-of-the-art techniques such as channel shortening and the relaxed multichannel least-squares method in terms of robustness to channel estimation errors.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Multi-microphone speech dereverberation and noise reduction using relative early transfer functions
TL;DR: A novel algorithm to simultaneously suppress early reflections, late reverberation and ambient noise is presented, and a multi-microphone minimum mean square error estimator is used to obtain a spatially filtered version of the early speech component.
88
A multichannel diffuse power estimator for dereverberation in the presence of multiple sources
TL;DR: In this article, a method is proposed to estimate the diffuse sound PSD from a set of reference signals by blocking the direct signal components, which is suitable in the presence of multiple simultaneously active speakers.
An expectation-maximization algorithm for multimicrophone speech dereverberation and noise reduction with coherence matrix estimation
TL;DR: In this paper, a novel algorithm to simultaneously suppress early reflections, late reverberation, and ambient noise is presented and it is shown that significant improvement is obtained and that the proposed algorithm outperforms baseline single-channel and multichannel dereverberation algorithms, as well as a state-of-the-art multich channel derever beration algorithm.
37
•Proceedings Article
Robust speech dereverberation using subband multichannel least squares with variable relaxation
Felicia S. C. Lim,Patrick A. Naylor +1 more
- 01 Sep 2013
TL;DR: An equalizer employing variable relaxation within the framework of the relaxed multichannel least squares (RMCLS) algorithm in frequency subbands is presented, showing that varying the relaxation of constraints in RMCLS leads to a trade-off between robustness to SIEs and improved suppression of the early reflections.
Relaxed Multichannel Least Squares with Constrained Initial Taps for Multichannel Dereverberation
Felicia S. C. Lim,Patrick A. Naylor +1 more
- 25 Sep 2012
TL;DR: It is shown through quantitative experimental results that the resultant equalized signal has an overall improved speech quality perception when compared to alternative algorithms.
References
Inverse filtering of room acoustics
Masato Miyoshi,Yutaka Kaneda +1 more
TL;DR: In this article, a novel method is proposed for realizing exact inverse filtering of acoustic impulse responses in room, based on the principle called the multiple-input/output inverse theorem (MINT).
767
An objective technique for evaluating doubletalk detectors in acoustic echo cancelers
TL;DR: A way to objectively evaluate DTD algorithms based on the standard statistical methods of detection theory is developed and a receiver operating characteristic (ROC) is derived to characterize DTD performance.
133
Inverse filtering for speech dereverberation less sensitive to noise
Takafumi Hikichi,Marc Delcroix,Masato Miyoshi +2 more
- 01 Jan 2006
TL;DR: In this article, the authors proposed reducing the energy of the inverse filter to make the filter less sensitive to room transfer functions (RTFs) fluctuations, and the experimental results show that the proposed method is effective in the presence of additive noise, as well as RTF fluctuations.
75
•Proceedings Article
Analyzing effect of noise on LMS-type approaches to blind estimation of simo channels: Robustness issue
Md. Kamrul Hasan,Patrick A. Naylor +1 more
- 01 Sep 2006
TL;DR: Experimental results demonstrate that the robustness of the blind adaptive algorithms can be significantly improved using a frequency domain energy constraint in the adaptation rule, and a novel technique for ameliorating misconvergence characteristic.
•Journal Article
Iterative Inverse Filter Relaxation Algorithm for Adaptation to Acoustic Fluctuation in Sound Reproduction System
TL;DR: A relaxation algorithm for an inverse filter that is adaptive to environmental change in a multichannel sound reproduction system and finds that the sound quality was found to be improved significantly without damaging the sound localization of position.
5