2013 |
I. Rodomagoulakis, P. Giannoulis, Z. I. Skordilis, P. Maragos, G. Potamianos Experiments on far-field multichannel speech processing in smart homes Conference 2013 18th International Conference on Digital Signal Processing, DSP 2013, 2013, ISBN: 9781467358057. @conference{175, title = {Experiments on far-field multichannel speech processing in smart homes}, author = { I. Rodomagoulakis and P. Giannoulis and Z. I. Skordilis and P. Maragos and G. Potamianos}, url = {http://robotics.ntua.gr/wp-content/uploads/publications/RGSMP_ExperimsFarfieldMultichannelSpeechProcessSmartHomes_DSP2013.pdf}, doi = {10.1109/ICDSP.2013.6622707}, isbn = {9781467358057}, year = {2013}, date = {2013-01-01}, booktitle = {2013 18th International Conference on Digital Signal Processing, DSP 2013}, keywords = {}, pubstate = {published}, tppubtype = {conference} } |
2007 |
Stamatios Lefkimmiatis, Petros Maragos A generalized estimation approach for linear and nonlinear microphone array post-filters Journal Article Speech Communication, 49 (7-8), pp. 657–666, 2007, ISSN: 01676393. Abstract | BibTeX | Links: [PDF] @article{124, title = {A generalized estimation approach for linear and nonlinear microphone array post-filters}, author = {Stamatios Lefkimmiatis and Petros Maragos}, url = {https://www.scopus.com/inward/record.url?eid=2-s2.0-34447096369&partnerID=40&md5=2a28c43abbc35eb2d516a43e23ea6602http://robotics.ntua.gr/wp-content/uploads/sites/2/LefkimmiatisMaragos_GeneralizedEstimationMicrophoneArrays_specom2007.pdf}, doi = {10.1016/j.specom.2007.02.004}, issn = {01676393}, year = {2007}, date = {2007-01-01}, journal = {Speech Communication}, volume = {49}, number = {7-8}, pages = {657--666}, abstract = {This paper presents a robust and general method for estimating the transfer functions of microphone array post-filters, derived under various speech enhancement criteria. For the case of the mean square error (MSE) criterion, the proposed method is an improvement of the existing McCowan post-filter, which under the assumption of a known noise field coherence function uses the auto- and cross-spectral densities of the microphone array noisy inputs to estimate the Wiener post-filter transfer function. In contrast to McCowan post-filter, the proposed method takes into account the noise reduction performed by the minimum variance distortionless response (MVDR) beamformer and obtains a more accurate estimation of the noise spectral density. Furthermore, the proposed estimation approach is general and can be used for the derivation of both linear and nonlinear microphone array post-filters, according to the utilized enhancement criterion. In experiments with real noise multichannel recordings the proposed technique has shown to obtain a significant gain over the other studied methods in terms of five different objective speech quality measures. textcopyright 2007 Elsevier B.V. All rights reserved.}, keywords = {}, pubstate = {published}, tppubtype = {article} } This paper presents a robust and general method for estimating the transfer functions of microphone array post-filters, derived under various speech enhancement criteria. For the case of the mean square error (MSE) criterion, the proposed method is an improvement of the existing McCowan post-filter, which under the assumption of a known noise field coherence function uses the auto- and cross-spectral densities of the microphone array noisy inputs to estimate the Wiener post-filter transfer function. In contrast to McCowan post-filter, the proposed method takes into account the noise reduction performed by the minimum variance distortionless response (MVDR) beamformer and obtains a more accurate estimation of the noise spectral density. Furthermore, the proposed estimation approach is general and can be used for the derivation of both linear and nonlinear microphone array post-filters, according to the utilized enhancement criterion. In experiments with real noise multichannel recordings the proposed technique has shown to obtain a significant gain over the other studied methods in terms of five different objective speech quality measures. textcopyright 2007 Elsevier B.V. All rights reserved. |
Copyright Notice:
Some material presented is available for download to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author’s copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.
The work already published by the IEEE is under its copyright. Personal use of such material is permitted. However, permission to reprint/republish the material for advertising or promotional purposes, or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of the work in other works must be obtained from the IEEE.