Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/95585
Title: | Multisource i-vectors domain adaptation using maximum mean discrepancy based autoencoders | Authors: | Lin, WW Mak, MW Chien, JT |
Issue Date: | Dec-2018 | Source: | IEEE/ACM transactions on audio, speech, and language processing, Dec. 2018, v. 26, no. 12, 8445620, p. 2412-2422 | Abstract: | Like many machine learning tasks, the performance of speaker verification (SV) systems degrades when training and test data come from very different distributions. What's more, both training and test data themselves could be composed of heterogeneous subsets. These multisource mismatches are detrimental to SV performance. This paper proposes incorporating maximum mean discrepancy (MMD) into the loss function of autoencoders to reduce these mismatches. MMD is a nonparametric method for measuring the distance between two probability distributions. With a properly chosen kernel, MMD can match up to infinite moments of data distributions. We generalize MMD to measure the discrepancies of multiple distributions.We call the generalized MMDdomainwiseMMD. Using domainwiseMMDas an objective function, we propose two autoencoders, namely nuisance-attribute autoencoder (NAE) and domain-invariant autoencoder (DAE), for multisource i-vector adaptation. NAE encodes the features that cause most of the multisource mismatch measured by domainwise MMD. DAE directly encodes the features that minimize the multisource mismatch. Using these MMD-based autoencoders as a preprocessing step for PLDA training, we achieve a relative improvement of 19.2% EER on the NIST 2016 SRE compared to PLDA without adaptation. We also found that MMD-based autoencoders are more robust to unseen domains. In the domain robustness experiments, MMD-based autoencoders show 6.8% and 5.2% improvements over IDVC on female and male Cantonese speakers, respectively. | Keywords: | Domain adaptation I-vectors Maximum mean discrepancy Speaker verification |
Publisher: | Institute of Electrical and Electronics Engineers | Journal: | IEEE/ACM transactions on audio, speech, and language processing | ISSN: | 2329-9290 | EISSN: | 2329-9304 | DOI: | 10.1109/TASLP.2018.2866707 | 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 W. Lin, M. Mak and J. Chien, "Multisource I-Vectors Domain Adaptation Using Maximum Mean Discrepancy Based Autoencoders," in IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 26, no. 12, pp. 2412-2422, Dec. 2018 is available at https://doi.org/10.1109/TASLP.2018.2866707. |
Appears in Collections: | Journal/Magazine Article |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Lin_Multisource_I-Vectors_Domain.pdf | Pre-Published version | 1.28 MB | Adobe PDF | View/Open |
Page views
59
Last Week
0
0
Last month
Citations as of Oct 13, 2024
Downloads
120
Citations as of Oct 13, 2024
SCOPUSTM
Citations
49
Citations as of Oct 17, 2024
WEB OF SCIENCETM
Citations
42
Citations as of Oct 10, 2024
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.