Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/107180
DC Field | Value | Language |
---|---|---|
dc.contributor | Department of Electrical and Electronic Engineering | - |
dc.creator | Lin, W | en_US |
dc.creator | Mak, MW | en_US |
dc.creator | Tu, Y | en_US |
dc.creator | Chien, JT | en_US |
dc.date.accessioned | 2024-06-13T01:04:25Z | - |
dc.date.available | 2024-06-13T01:04:25Z | - |
dc.identifier.isbn | 978-1-4799-8131-1 (Electronic) | en_US |
dc.identifier.isbn | 978-1-4799-8132-8 (Print on Demand(PoD)) | en_US |
dc.identifier.uri | http://hdl.handle.net/10397/107180 | - |
dc.description | ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 12-17 May 2019, Brighton, UK | en_US |
dc.language.iso | en | en_US |
dc.publisher | Institute of Electrical and Electronics Engineers | en_US |
dc.rights | ©2019 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. | en_US |
dc.rights | The following publication W. Lin, M. -W. Mak, Y. Tu and J. -T. Chien, "Semi-supervised Nuisance-attribute Networks for Domain Adaptation," ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK, 2019, pp. 6236-6240 is available at https://doi.org/10.1109/ICASSP.2019.8682752. | en_US |
dc.subject | Domain adaptation | en_US |
dc.subject | I-vectors | en_US |
dc.subject | Maximum mean discrepancy | en_US |
dc.subject | Speaker verification | en_US |
dc.subject | X-vectors | en_US |
dc.title | Semi-supervised nuisance-attribute networks for domain adaptation | en_US |
dc.type | Conference Paper | en_US |
dc.identifier.spage | 6236 | en_US |
dc.identifier.epage | 6240 | en_US |
dc.identifier.doi | 10.1109/ICASSP.2019.8682752 | en_US |
dcterms.abstract | How to overcome the training and test data mismatch in speaker verification systems has been a focus of research recently. In this paper, we propose a semi-supervised nuisance attribute network (SNAN) to reduce the domain mismatch in i-vectors and x-vectors. SNANs are based on the idea of nuisance attribute removal in inter-dataset variability compensation (IDVC). But instead of measuring the domain variability through the dataset means, SNANs use the maximum mean discrepancy (MMD) as part of their loss function, which enables the network to find nuisance directions in which domain variability is measured up to infinite moment. The architecture of SNANs also allows us to incorporate the out-of-domain speaker labels into the semi-supervised training process through the center loss and triplet loss. Using SNANs as a preprocessing step for PLDA training, we achieve a relative improvement of 11.8% in EER on NIST 2016 SRE compared to PLDA without adaptation. We also found that the semi-supervised approach can further improve SNANs' performance. | - |
dcterms.accessRights | open access | en_US |
dcterms.bibliographicCitation | In Proceedings of ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 12-17 May 2019, Brighton, UK, p. 6236-6240 | en_US |
dcterms.issued | 2019 | - |
dc.identifier.scopus | 2-s2.0-85068959440 | - |
dc.relation.conference | International Conference on Acoustics, Speech, and Signal Processing [ICASSP] | - |
dc.description.validate | 202404 bckw | - |
dc.description.oa | Accepted Manuscript | en_US |
dc.identifier.FolderNumber | EIE-0383 | - |
dc.description.fundingSource | RGC | en_US |
dc.description.fundingSource | Others | en_US |
dc.description.fundingText | Taiwan MOST | en_US |
dc.description.pubStatus | Published | en_US |
dc.identifier.OPUS | 20150823 | - |
dc.description.oaCategory | Green (AAM) | en_US |
Appears in Collections: | Conference Paper |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Lin_Semi-Supervised_Nuisance-Attribute_Networks.pdf | Pre-Published version | 301.18 kB | Adobe PDF | View/Open |
Page views
2
Citations as of Jun 30, 2024
Downloads
1
Citations as of Jun 30, 2024
SCOPUSTM
Citations
6
Citations as of Jun 21, 2024
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.