Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/107243
Title: | Senone i-vectors for robust speaker verification | Authors: | Tan, Z Zhu, Y Mak, MW Mak, BKW |
Issue Date: | 2016 | Source: | In Proceedings of 2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP), 17-20 October 2016, Tianjin, China | Abstract: | Recent research has shown that using senone posteriors for i-vector extraction can achieve outstanding performance. In this paper, we extend this idea to robust speaker verification by constructing a deep neural network (DNN) comprising a deep belief network (DBN) stacked on top of a denoising autoencoder (DAE). The proposed method addresses noise robustness in two perspectives: (1) denoising the MFCC vectors through the DAE and (2) extracting noise robust bottleneck (BN) features and senone posteriors from the DBN for total-variability matrix training and i-vector extraction. The DAE comprises several layers of restricted Boltzmann machines (RBM), which are trained to minimize the mean squared error between the denoised and clean MFCCs. After training the DAE, three layers of RBMs are put on top of it to form the DNN. The whole network is fine-tuned by backpropagation to minimize the cross-entropy between the senone labels and network outputs. This architecture allows us to extract BN features and estimates senone posteriors given noisy MFCCs as input, resulting in robust BN-based senone i-vectors. Results on NIST 2012 SRE show that these senone i-vectors outperform the conventional i-vectors and the BN-based i-vectors in which the posteriors are obtained from a GMM. | Keywords: | Deep learning Denoising autoencoders I-vectors Senone posteriors Speaker verification |
Publisher: | Institute of Electrical and Electronics Engineers | ISBN: | 978-1-5090-4294-4 (Electronic) 978-1-5090-4295-1 (Print on Demand(PoD)) |
DOI: | 10.1109/ISCSLP.2016.7918462 | Description: | 2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP), 17-20 October 2016, Tianjin, China | Rights: | ©2016 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, Y. Zhu, M. -W. Mak and B. K. -W. Mak, "Senone I-vectors for robust speaker verification," 2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP), Tianjin, China, 2016 is available at https://doi.org/10.1109/ISCSLP.2016.7918462. |
Appears in Collections: | Conference Paper |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Tan_Senone_I-Vectors_Robust.pdf | Pre-Published version | 822.64 kB | Adobe PDF | View/Open |
Page views
7
Citations as of Jun 30, 2024
SCOPUSTM
Citations
5
Citations as of Jun 21, 2024
![](/image/google_scholar.jpg)
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.