DeepAI AI Chat
Log In Sign Up

Contrastive Predictive Coding Based Feature for Automatic Speaker Verification

by   Cheng-I Lai, et al.

This thesis describes our ongoing work on Contrastive Predictive Coding (CPC) features for speaker verification. CPC is a recently proposed representation learning framework based on predictive coding and noise contrastive estimation. We focus on incorporating CPC features into the standard automatic speaker verification systems, and we present our methods, experiments, and analysis. This thesis also details necessary background knowledge in past and recent work on automatic speaker verification systems, conventional speech features, and the motivation and techniques behind CPC.


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

Contrastive predictive coding (CPC) aims to learn representations of spe...

Semi-Supervised Contrastive Learning with Generalized Contrastive Loss and Its Application to Speaker Recognition

This paper introduces a semi-supervised contrastive learning framework a...

Momentum Contrast Speaker Representation Learning

Unsupervised representation learning has shown remarkable achievement by...

Powerful Speaker Embedding Training Framework by Adversarially Disentangled Identity Representation

The main challenge of speaker verification in the wild is the interferen...

Unsupervised Representation Learning for Speaker Recognition via Contrastive Equilibrium Learning

In this paper, we propose a simple but powerful unsupervised learning me...

Segmental Contrastive Predictive Coding for Unsupervised Word Segmentation

Automatic detection of phoneme or word-like units is one of the core obj...

When Automatic Voice Disguise Meets Automatic Speaker Verification

The technique of transforming voices in order to hide the real identity ...