JAIST Repository >
School of Information Science >
Conference Papers >
Conference Papers >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10119/16962

Title: Segment-level Effects of Gender, Nationality and Emotion Information on Text-independent Speaker Verification
Authors: Li, Kai
Akagi, Masato
Wu, Yibo
Dang, and Jianwu
Keywords: Multitask learning
Domain adversarial training
Speaker embedding
Text-independent speaker verification
Issue Date: 2020-10
Publisher: International Speech Communication Association
Magazine name: Proc. InterSpeech2020
Start page: 2987
End page: 2991
DOI: 10.21437/Interspeech.2020-1700
Abstract: Speaker embeddings extracted from neural network (NN) achieve excellent performance on general speaker verification (SV) missions. Most current SV systems use only speaker labels. Therefore, the interaction between different types of domain information decrease the prediction accuracy of SV. To overcome this weakness and improve SV performance, four effective SV systems were proposed by using gender, nationality, and emotion information to add more constraints in the NN training stage. More specifically, multitask learning-based systems which including multitask gender (MTG), multitask nationality (MTN) and multitask gender and nationality (MTGN) were used to enhance gender and nationality information learning. Domain adversarial training-based system which including emotion domain adversarial training (EDAT) was used to suppress different emotions information learning. Experimental results indicate that encouraging gender and nationality information and suppressing emotion information learning improve the performance of SV. In the end, our proposed systems achieved 16.4 and 22.9% relative improvements in the equal error rate for MTL- and DAT-based systems, respectively.
Rights: Copyright (C) 2020 International Speech Communication Association. Kai Li, Masato Akagi, Yibo Wu, and Jianwu Dang, Proc. InterSpeech2020, 2020, pp.2987-2991. http://dx.doi.org/10.21437/Interspeech.2020-1700
URI: http://hdl.handle.net/10119/16962
Material Type: publisher
Appears in Collections:b11-1. 会議発表論文・発表資料 (Conference Papers)

Files in This Item:

File Description SizeFormat
3357.pdf439KbAdobe PDFView/Open

All items in DSpace are protected by copyright, with all rights reserved.

 


Contact : Library Information Section, JAIST (ir-sys[at]ml.jaist.ac.jp)