Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/95586
Title: | Discriminative subspace modeling of SNR and duration variabilities for robust speaker verification | Authors: | Li, N Mak, MW Lin, WW Chien, JT |
Issue Date: | Sep-2017 | Source: | Computer speech and language, Sept. 2017, v. 45, p. 83-103 | Abstract: | Although i-vectors together with probabilistic LDA (PLDA) have achieved a great success in speaker verification, how to suppress the undesirable effects caused by the variability in utterance length and background noise level is still a challenge. This paper aims to improve the robustness of i-vector based speaker verification systems by compensating for the utterance-length variability and noise-level variability. Inspired by the recent findings that noise-level variability can be modeled by a signal-to-noise ratio (SNR) subspace and that duration variability can be modeled as additive noise in the i-vector space, we propose to add an SNR factor and a duration factor to the PLDA model. In this framework, we assume that i-vectors derived from utterances with comparable durations share similar duration-specific information and that i-vectors extracted from utterances within a narrow SNR range have similar SNR-specific information. Based on these assumptions, an i-vector can be represented as a linear combination of four components: speaker, SNR, duration, and channel. A variational Bayes algorithm is developed to infer this latent variable model via a discriminative subspace training procedure. In the testing stage, different variabilities are compensated for when computing the likelihood ratio. Experiments on Common Conditions 1 and 4 in NIST 2012 SRE show that the proposed model outperforms the conventional PLDA and SNR-invariant PLDA. Results also show that the proposed model performs better than the uncertainty-propagation PLDA (UP-PLDA) for long test utterances. | Keywords: | Duration variation I-vector PLDA SNR mismatch Speaker verification Variational Bayes |
Publisher: | Academic Press | Journal: | Computer speech and language | ISSN: | 0885-2308 | DOI: | 10.1016/j.csl.2017.04.001 | Rights: | © 2017 Elsevier Ltd. All rights reserved. © 2017. This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/. The following publication Li, N., Mak, M. W., Lin, W. W., & Chien, J. T. (2017). Discriminative subspace modeling of SNR and duration variabilities for robust speaker verification. Computer Speech & Language, 45, 83-103 is available at https://doi.org/10.1016/j.csl.2017.04.001. |
Appears in Collections: | Journal/Magazine Article |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Mak_Discriminative_Subspace_Modeling.pdf | Pre-Published version | 2.34 MB | Adobe PDF | View/Open |
Page views
34
Last Week
0
0
Last month
Citations as of Oct 13, 2024
Downloads
56
Citations as of Oct 13, 2024
SCOPUSTM
Citations
7
Citations as of Oct 17, 2024
WEB OF SCIENCETM
Citations
5
Citations as of Oct 10, 2024
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.