Variational Domain Adversarial Learning With Mutual Information Maximization for Speaker Verification
檔案
本條目沒有附加檔案。
日期
2020-01-01
類型
系所
期刊名稱
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING
卷期與頁次
第 28 卷,頁 2013–2024
ISSN
2329-9290
語言
英文
摘要
Domain mismatch is a common problem in speaker verification (SV) and often causes performance degradation. For the system relying on the Gaussian PLDA backend to suppress the channel variability, the performance would be further limited if there is no Gaussianity constraint on the learned embeddings. This paper proposes an information-maximized variational domain adversarial neural network (InfoVDANN) that incorporates an InfoVAE into domain adversarial training (DAT) to reduce domain mismatch and simultaneously meet the Gaussianity requirement of the PLDA backend. Specifically, DAT is applied to produce speaker discriminative and domain-invariant features, while the InfoVAE performs variational regularization on the embedded features so that they follow a Gaussian distribution. Another benefit of the InfoVAE is that it avoids posterior collapse in VAEs by preserving the mutual information between the embedded features and the training set so that extra speaker information can be retained in the features. Experiments on both SRE16 and SRE18-CMN2 show that the InfoVDANN outperforms the recent VDANN, which suggests that increasing the mutual information between the embedded features and input features enables the InfoVDANN to extract extra speaker information that is otherwise not possible.
關鍵詞
Speaker verification (SV)domain adaptationdomain adversarial trainingvariational autoencodermutual information所屬典藏
期刊論文引用此條目
Tu, Y., Mak, M.-W., & Chien, J.-T. (2020). Variational Domain Adversarial Learning With Mutual Information Maximization for Speaker Verification. IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 28, 2013–2024. https://doi.org/10.1109/TASLP.2020.3004760
引用文字依 APA 第 7 版格式自動產生,使用前請再核對。
分享
永久網址:https://ir.lib.nycu.edu.tw/handle/11536/154890