2023
DOI: 10.1109/taslp.2023.3268568
|View full text |Cite
|
Sign up to set email alerts
|

Self-Supervised Training of Speaker Encoder With Multi-Modal Diverse Positive Pairs

Abstract: We study a novel neural speaker encoder and its training strategies for speaker recognition without using any identity labels. The speaker encoder is trained to extract a fixed dimensional speaker embedding from a spoken utterance of variable length. Contrastive learning is a typical self-supervised learning technique. However, the contrastive learning of the speaker encoder depends very much on the sampling strategy of positive and negative pairs. It is common that we sample a positive pair of segments from t… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

0
0
0

Year Published

2024
2024
2024
2024

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
references
References 60 publications
(92 reference statements)
0
0
0
Order By: Relevance