Contrastive Predictive Coding Based Feature for Automatic Speaker Verification

Abstract

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.

Cited by in corpus (7)

• Data Augmenting Contrastive Learning of Speech Representations in the Time Domain
• ReSSL: Relational Self-Supervised Learning with Weak Augmentation
• PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition
• Towards Semi-Supervised Semantics Understanding from Speech
• SIRL: Similarity-based Implicit Representation Learning
• MSVQ: Self-Supervised Learning with Multiple Sample Views and Queues
• A Comparison of Discrete Latent Variable Models for Speech Representation Learning