.png){kind=icon}
返回
Augmentation Adversarial Training for Self-Supervised Speaker Representation Learning
.png){kind=icon}
PRE
AI
DOI：10.1109/JSTSP.2022.3200915.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The goal of this work is to train robust speaker recognition models using self-supervised representation learning. Recent works on self-supervised speaker representations are based on contrastive learning in which they encourage within-utterance embeddings to be similar and across-utterance embeddings to be dissimilar. However, since the within-utterance segments share the same acoustic characteristics, it is difficult to separate the speaker information from the channel information. To this end, we propose an augmentation adversarial training strategy that trains the network to be discriminative for the speaker information, while invariant to the augmentation applied. Since the augmentation simulates the acoustic characteristics, training the network to be invariant to augmentation also encourages the network to be invariant to the channel information in general. Extensive experiments on the VoxCeleb and VOiCES datasets show significant improvements over previous works using self-supervision, and the performance of our self-supervised models far exceeds that of humans. We also conduct semi-supervised learning experiments to show that augmentation adversarial training benefits performance in presence of speaker labels.
Keyword:
Training
Speaker recognition
Measurement
Task analysis
Semisupervised learning
Representation learning
Entropy
Self-supervised learning
speaker recognition
期刊
IF:
13.7
论文数:
1.9K
被引数:
1.1W
机构
引用论文
.png){kind=icon}
Types of Parent Verbal Responsiveness That Predict Language in Young Children With Autism Spectrum Disorder预测自闭症谱系障碍幼儿语言的父母言语反应类型
OAAI
OAAI分享收藏The shadow economy in three Mediterranean countries: France, Spain and Greece. A MIMIC approach
PREAI
分享收藏
查看更多内容