Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/77313
| Title: | DNN-Based score calibration with multitask learning for noise robust speaker verification | Authors: | Tan, Z Mak, MW Mak, BKW |
Issue Date: | Apr-2018 | Source: | IEEE/ACM transactions on audio, speech, and language processing, Apr. 2018, v. 26, no. 48249870, p. 700-712 | Abstract: | This paper proposes and investigates several deep neural network (DNN) based score compensation, transformation, and calibration algorithms for enhancing the noise robustness of i-vector speaker verification systems. Unlike conventional calibration methods where the required score shift is a linear function of SNR or log-duration, the DNN approach learns the complex relationship between the score shifts and the combination of i-vector pairs and uncalibrated scores. Furthermore, with the flexibility of DNNs, it is possible to explicitly train a DNN to recover the clean scores without having to estimate the score shifts. To alleviate the overfitting problem, multitask learning is applied to incorporate auxiliary information such as SNRs and speaker ID of training utterances into the DNN. Experiments on NIST 2012 SRE show that score calibration derived from multitask DNNs can improve the performance of the conventional score-shift approch significantly, especially under noisy conditions. | Keywords: | Deep learning Multi-task learning Noise robustness Score calibration 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.2018.2791105 | 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 Z. Tan, M. Mak and B. K. Mak, "DNN-Based Score Calibration With Multitask Learning for Noise Robust Speaker Verification," in IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 26, no. 4, pp. 700-712, April 2018 is available at https://doi.org/10.1109/TASLP.2018.2791105. |
| Appears in Collections: | Journal/Magazine Article |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| Tan_Dnn-Based_Score_Calibration.pdf | Pre-Published version | 1.4 MB | Adobe PDF | View/Open |
Access
View full-text via PolyU eLinks 
Page views
89
Last Week
0
0
Last month
Citations as of Sep 24, 2023
Downloads
18
Citations as of Sep 24, 2023
SCOPUSTM
Citations
7
Citations as of Sep 21, 2023
WEB OF SCIENCETM
Citations
6
Last Week
0
0
Last month
Citations as of Sep 21, 2023
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.