Please use this identifier to cite or link to this item:
|Title:||A joint-loss approach for speech enhancement via single-channel neural network and MVDR beamformer||Authors:||Tan, Zhi-Wei
Nguyen, Anh Hai Trieu
Tran, Linh T. T.
Khong, Andy Wai Hoong
|Keywords:||Engineering||Issue Date:||2020||Source:||Tan, Z.-W., Nguyen, A. H. T., Tran, L. T. T., & Khong, A. W. H. (2020). A joint-loss approach for speech enhancement via single-channel neural network and MVDR beamformer. Proceedings of the Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 841-849.||Project:||MRP14||metadata.dc.contributor.conference:||2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)||Abstract:||Recent developments of noise reduction involves the use of neural beamforming. While some success is achieved, these algorithms rely solely on the gain of the beamformer to enhance the noisy signals. We propose a framework that comprises two stages where the first-stage neural network aims to achieve a good estimate of the signal and noise to the secondstage beamformer. We also introduce an objective function that reduces the distortion of the speech component in each stage. This objective function improves the accuracy of the secondstage beamformer by enhancing the first-stage output, and in the second stage, enhances the training of the network by propagating the gradient through the beamforming operation. A parameter is introduced to control the trade-off between optimizing these two stages. Simulation results on the CHiME-3 dataset at low-SNR show that the proposed algorithm is able to exploit the enhancement gains from the neural network and the beamformer with improvement over other baseline algorithms in terms of speech distortion, quality and intelligibility.||URI:||https://hdl.handle.net/10356/146260||Schools:||School of Electrical and Electronic Engineering||Research Centres:||ST Engineering-NTU Corporate Lab||Rights:||© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.||Fulltext Permission:||open||Fulltext Availability:||With Fulltext|
|Appears in Collections:||EEE Conference Papers|
Updated on Sep 29, 2023
Updated on Sep 29, 2023
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.