DeepAI AI Chat
Log In Sign Up

Powerful Speaker Embedding Training Framework by Adversarially Disentangled Identity Representation

11/27/2019
by   Jianwei Tai, et al.
iie.ac.cn
The Chinese University of Hong Kong
0

The main challenge of speaker verification in the wild is the interference caused by irrelevant information in speech and the lack of speaker labels in speech datasets. In order to solve the above problems, we propose a novel speaker embedding training framework based on adversarially disentangled identity representation. Our key insight is to adversarially learn the identity-purified features for speaker verification, and learn an identity-irrelated feature whose speaker information cannot be distinguished. Based on the existing state-of-the-art speaker verification models, we improve them without adjusting the structure and hyper-parameters of any model. Experiments prove that the framework we propose can significantly improve the performance of speaker verification from the original model without any empirical adjustments. Proving that it is particularly useful for alleviating the lack of speaker labels.

READ FULL TEXT
08/04/2020

MIRNet: Learning multiple identities representations in overlapped speech

Many approaches can derive information about a single speaker's identity...
02/10/2020

An empirical analysis of information encoded in disentangled neural speaker representations

The primary characteristic of robust speaker representations is that the...
08/07/2020

Disentangled speaker and nuisance attribute embedding for robust speaker verification

Over the recent years, various deep learning-based embedding methods hav...
08/17/2022

Disentangled Speaker Representation Learning via Mutual Information Minimization

Domain mismatch problem caused by speaker-unrelated feature has been a m...
08/02/2021

Analyzing Speaker Information in Self-Supervised Models to Improve Zero-Resource Speech Processing

Contrastive predictive coding (CPC) aims to learn representations of spe...
04/01/2019

Contrastive Predictive Coding Based Feature for Automatic Speaker Verification

This thesis describes our ongoing work on Contrastive Predictive Coding ...
03/28/2023

A Universal Identity Backdoor Attack against Speaker Verification based on Siamese Network

Speaker verification has been widely used in many authentication scenari...