Speaker diarization based on multi-timescale feature fusion

Futian Wang; Lailong Chen

doi:10.1117/12.2674733

2 May 2023 Speaker diarization based on multi-timescale feature fusion

Futian Wang, Lailong Chen

Proceedings Volume 12642, Second International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2023); 126422K (2023) https://doi.org/10.1117/12.2674733
Event: Second International Conference on Electronic Information Engineering, Big Data and Computer Technology (EIBDCT 2023), 2023, Xishuangbanna, China

Abstract

Deep and convolutional neural networks have performed well in capturing speaker characteristics, while the ECAPA-TDNN model has demonstrated outstanding performance in both the fields of speaker validation and speaker diarization. Within this essay, during the speech segmentation stage, we uniformly redivide the speech on multiple time scales based on the oracle voice activity detection. Meanwhile, we fine-tune the ECAPA-TDNN architecture by adding a RepVGG module to extract more abundant features, then aggregate all of the outputs. Finally, we use DOVER-Lap to integrate the results obtained after the clustering of multiple schemes in a way to obtain the final temporal labeling. The best results achieves 1.91% of the diarization error rate on the classical AMI conference corpus.

Citation Download Citation

Futian Wang and Lailong Chen "Speaker diarization based on multi-timescale feature fusion", Proc. SPIE 12642, Second International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2023), 126422K (2 May 2023); https://doi.org/10.1117/12.2674733

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