Prototypical networks for small footprint text-independent speaker verification

Ko，Tom1; Chen，Yangbin2; Li，Qing3

10.1109/ICASSP40776.2020.9054471

2020-05-01

1520-6149

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

2020-May

6804-6808

Speaker verification aims to recognize target speakers with very few enrollment utterances. Conventional approaches learn a representation model to extract the speaker embeddings for verification. Recently, there are several new approaches in meta-learning which try to learn a shared metric space. Among these approaches, prototypical networks aim at learning a non-linear mapping from the input space to an embedding space with a predefined distance metric. In this paper, we investigate the use of prototypical networks in a small footprint text-independent speaker verification task. Our work is evaluated on SRE10 evaluation set. Experiments show that prototypical networks outperform the conventional method when the amount of data per training speaker is limited.

Meta learning Prototypical networks Speaker verification

第一

英语

EI

20203909217088

Speech recognition ; Computer vision

Artificial Intelligence:723.4 ; Computer Applications:723.5 ; Vision:741.2 ; Speech:751.5

2-s2.0-85091147221

Scopus

1.Department of Computer Science and Engineering,South University of Science and Technology,Shenzhen,China
2.Department of Computer Science,City University of Hong Kong,Hong Kong
3.Department of Computing,Hong Kong Polytechnic University,Hong Kong

Ko，Tom,Chen，Yangbin,Li，Qing. Prototypical networks for small footprint text-independent speaker verification[C],2020:6804-6808.