Attentive deep CNN for speaker verification

Yong-bin Yu; Min-hui Qi; Yi-fan Tang; Quan-xin Deng; Chen-hui Peng; Feng Mai; Tashi Nyima

doi:10.1117/12.2581351

20 January 2021 Attentive deep CNN for speaker verification

Yong-bin Yu, Min-hui Qi, Yi-fan Tang, Quan-xin Deng, Chen-hui Peng, Feng Mai, Tashi Nyima

Proceedings Volume 11719, Twelfth International Conference on Signal Processing Systems; 117190U (2021) https://doi.org/10.1117/12.2581351
Event: Twelfth International Conference on Signal Processing Systems, 2020, Shanghai, China

Abstract

In this paper, an end-to-end speaker verification system based on attentive deep convolutional neural network (CNN) is highlighted. It takes log filter bank coefficients as input and measures speaker similarity between a test utterance and enrollment utterances by cosine similarity for verification. The approach utilizes the channel attention module of convolutional block attention module (CBAM) to increase representation power by giving different weights to feature maps. In addition, softmax is used to pre-train for initializing the weights of the network and tuple-based end-to-end (TE2E) loss function is responsible for fine-tune in evaluation stage, such a strategy not only results in notable improvements over the baseline model but also allows for direct optimization of the evaluation metric. Experimental results on VoxCeleb dataset indicates that proposed model achieves an equal error rate (EER) of 3.83%, which is slightly worse than x-vectors while outperforms i-vectors.

Citation Download Citation

Yong-bin Yu, Min-hui Qi, Yi-fan Tang, Quan-xin Deng, Chen-hui Peng, Feng Mai, and Tashi Nyima "Attentive deep CNN for speaker verification", Proc. SPIE 11719, Twelfth International Conference on Signal Processing Systems, 117190U (20 January 2021); https://doi.org/10.1117/12.2581351

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available