Introducing phonetic information to speaker embedding for speaker verification

Introducing phonetic information to speaker embedding for speaker verification

Abstract Phonetic information is one of the most essential components of a speech signal, playing an important role for many speech processing tasks. However, it is difficult to integrate phonetic information into speaker verification systems since it occurs primarily at the frame level while speake...

Full description

Bibliographic Details
Main Authors: Yi Liu, Liang He, Jia Liu, Michael T. Johnson
Format: Article
Language:English
Published: SpringerOpen 2019-12-01
Series:EURASIP Journal on Audio, Speech, and Music Processing
Subjects:
Speaker verification
Deep neural networks
Speaker embedding
Phonetic adaptation
Multi-task learning
C-vector
Online Access:https://doi.org/10.1186/s13636-019-0166-8

Internet

https://doi.org/10.1186/s13636-019-0166-8

Similar Items