DT-SV: A Transformer-based Time-domain Approach for Speaker Verification-Reference-Cited by-同舟云学术

DT-SV: A Transformer-based Time-domain Approach for Speaker Verification

Author:

Zhang Nan¹,Wang Jianzong¹,Hong Zhenhou¹,Zhao Chendong¹,Qu Xiaoyang¹,Xiao Jing¹

Affiliation:

1. Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China

Funder

Key Research and Development Program of Guangdong Province

Publisher

IEEE

Link

Reference39 articles.

2. Raw-x-vector: Multi-scale time domain speaker embedding network;zhu;ArXiv Preprint,2020

5. Adam: A method for stochastic optimization;kingma;ArXiv Preprint,2014

Cited by 3 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Improving Transformer-Based Networks with Locality for Automatic Speaker Verification;ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2023-06-04

2. Max-Pooling Based Self-Attention with Transformer for Speaker Verification;2023 7th International Conference on Machine Vision and Information Technology (CMVIT);2023-03

3. Adaptive Sparse and Monotonic Attention for Transformer-based Automatic Speech Recognition;2022 IEEE 9th International Conference on Data Science and Advanced Analytics (DSAA);2022-10-13