TY - GEN
T1 - ECAPA-TDNN Embeddings for Speaker Recognition
AU - Guo, Jingxiang
AU - Zhu, Jinxuan
AU - Lin, Sixu
AU - Shi, Feng
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - This paper proposes novel robust speaker recognition pipelines to tackle the problem of far-field speaker recognition in reverberation and noise to the Robovox dataset. Specifically, we explored methods including I-vector, X-vector, and ECAPA-TDNN, with the ECAPA-TDNN method demonstrating exceptional performance. The paper details the comprehensive process of our preparation and experiment.
AB - This paper proposes novel robust speaker recognition pipelines to tackle the problem of far-field speaker recognition in reverberation and noise to the Robovox dataset. Specifically, we explored methods including I-vector, X-vector, and ECAPA-TDNN, with the ECAPA-TDNN method demonstrating exceptional performance. The paper details the comprehensive process of our preparation and experiment.
KW - Aggregation in TDNN (ECAPA-TDNN)
KW - Emphasized Channel Attention
KW - Propagation
KW - Speaker Recognition
KW - Time Delay Neural Networks (TDNN)
UR - https://www.scopus.com/pages/publications/85199137287
U2 - 10.1109/AINIT61980.2024.10581514
DO - 10.1109/AINIT61980.2024.10581514
M3 - 会议稿件
AN - SCOPUS:85199137287
T3 - 2024 5th International Seminar on Artificial Intelligence, Networking and Information Technology, AINIT 2024
SP - 1488
EP - 1491
BT - 2024 5th International Seminar on Artificial Intelligence, Networking and Information Technology, AINIT 2024
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 5th International Seminar on Artificial Intelligence, Networking and Information Technology, AINIT 2024
Y2 - 29 May 2024 through 31 May 2024
ER -