Masked multi-center angular margin loss for language recognition

Masked multi-center angular margin loss for language recognition

Abstract Language recognition based on embedding aims to maximize inter-class variance and minimize intra-class variance. Previous researches are limited to the training constraint of a single centroid, which cannot accurately describe the overall geometric characteristics of the embedding space. In...

Full description

Bibliographic Details
Main Authors: Minghang Ju, Yanyan Xu, Dengfeng Ke, Kaile Su
Format: Article
Language:English
Published: SpringerOpen 2022-07-01
Series:EURASIP Journal on Audio, Speech, and Music Processing
Subjects:
Spoken language recognition
Masked multi-center angular margin
Multi-center loss
Single-center loss
ECAPA-TDNN neural network
Online Access:https://doi.org/10.1186/s13636-022-00249-4

Internet

https://doi.org/10.1186/s13636-022-00249-4

Similar Items