Skip to main content

Improved Conditional Generative Adversarial Net Classification For Spoken Language Recognition

Miao, Xiaoxiao, McLoughlin, Ian Vince, Yao, Shengyu, Yan, Yonghong (2018) Improved Conditional Generative Adversarial Net Classification For Spoken Language Recognition. In: 2018 IEEE Workshop on Spoken Language Technology SLT 2018 Proceedings. . IEEE ISBN 978-1-5386-4334-1. (doi:10.1109/SLT.2018.8639522)

PDF - Author's Accepted Manuscript
Download (524kB) Preview
[img]
Preview
Official URL
http://dx.doi.org/10.1109/SLT.2018.8639522

Abstract

Recent research on generative adversarial nets (GAN) for language identification (LID) has shown promising results. In this paper, we further exploit the latent abilities of GAN networks to firstly combine them with deep neural network (DNN)-based i-vector approaches and then to improve the LID model using conditional generative adversarial net (cGAN) classification. First, phoneme dependent deep bottleneck features (DBF) combined with output posteriors of a pre-trained DNN for automatic speech recognition (ASR) are used to extract i-vectors in the normal way. These i-vectors are then classified using cGAN, and we show an effective method within the cGAN to optimize parameters by combining both language identification and verification signals as supervision. Results show firstly that cGAN methods can significantly outperform DBF DNN i-vector methods where 49-dimensional i-vectors are used, but not where 600-dimensional vectors are used. Secondly, training a cGAN discriminator network for direct classification has further benefit for low dimensional i-vectors as well as short utterances with high dimensional i-vectors. However, incorporating a dedicated discriminator network output layer for classification and optimizing both classification and verification loss brings benefits in all test cases.

Item Type: Conference or workshop item (Proceeding)
DOI/Identification number: 10.1109/SLT.2018.8639522
Uncontrolled keywords: Language identification
Subjects: T Technology
Divisions: Faculties > Sciences > School of Computing
Faculties > Sciences > School of Computing > Data Science
Depositing User: Ian McLoughlin
Date Deposited: 13 Sep 2018 20:14 UTC
Last Modified: 29 May 2019 21:09 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/69101 (The current URI for this page, for reference purposes)
McLoughlin, Ian Vince: https://orcid.org/0000-0001-7111-2008
  • Depositors only (login required):

Downloads

Downloads per month over past year