Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/107190
Title: | SNR-invariant multitask deep neural networks for robust speaker verification | Authors: | Yao, Q Mak, MW |
Issue Date: | Nov-2018 | Source: | IEEE signal processing letters, Nov. 2018, v. 25, no. 11, p. 1670-1674 | Abstract: | A major challenge in speaker verification is to achieve low error rates under noisy environments. We observed that background noise in utterances will not only enlarge the speaker-dependent i-vector clusters but also shift the clusters, with the amount of shift depending on the signal-to-noise ratio (SNR) of the utterances. To overcome this SNR-dependent clustering phenomenon, we propose two deep neural network (DNN) architectures: hierarchical regression DNN (H-RDNN) and multitask DNN (MT-DNN). The H-RDNN is formed by stacking two regression DNNs in which the lower DNN is trained to map noisy i-vectors to their respective speaker-dependent cluster means of clean i-vectors and the upper DNN aims to regularize the outliers that cannot be denoised properly by the lower DNN. The MT-DNN is trained to denoise i-vectors (main task) and classify speakers (auxiliary task). The network leverages the auxiliary task to retain speaker information in the denoised i-vectors. Experimental results suggest that these two DNN architectures together with the PLDA backend significantly outperform the multicondition PLDA model and mixtures of PLDA, and that multitask learning helps to boost verification performance. | Keywords: | Deep learning I-vectors Multitask learning Noise robustness Speaker verification |
Publisher: | Institute of Electrical and Electronics Engineers | Journal: | IEEE signal processing letters | ISSN: | 1070-9908 | EISSN: | 1558-2361 | DOI: | 10.1109/LSP.2018.2870726 | Rights: | © 2018 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. The following publication Q. Yao and M. -W. Mak, "SNR-Invariant Multitask Deep Neural Networks for Robust Speaker Verification," in IEEE Signal Processing Letters, vol. 25, no. 11, pp. 1670-1674, Nov. 2018 is available at https://doi.org/10.1109/LSP.2018.2870726. |
Appears in Collections: | Journal/Magazine Article |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Yao_Snr-Invariant_Multitask_Deep.pdf | Pre-Published version | 814.52 kB | Adobe PDF | View/Open |
Page views
4
Citations as of Jun 30, 2024
Downloads
1
Citations as of Jun 30, 2024
SCOPUSTM
Citations
7
Citations as of Jun 21, 2024
WEB OF SCIENCETM
Citations
6
Citations as of Jun 27, 2024
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.