Unispeech-sat: Universal Speech Representation Learning With Speaker Aware Pre-training

Abstract

Self-supervised learning (SSL) is a long-standing goal for speech processing, since it utilizes large-scale unlabeled data and avoids extensive human labeling. Recent years witness great successes in applying self-supervised learning in speech recognition, while limited exploration was attempted in applying SSL for modeling speaker characteristics. In this paper, we aim to improve the existing SSL framework for speaker representation learning. Two methods are introduced for enhancing the unsupervised speaker information extraction. First, we apply the multi-task learning to the current SSL framework, where we integrate the utterance-wise contrastive loss with the SSL objective function. Second, for better speaker discrimination, we propose an utterance mixing strategy for data augmentation, where additional overlapped utterances are created unsupervisely and incorporate during training. We integrate the proposed methods into the HuBERT framework. Experiment results on SUPERB benchmark

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keychen2021unispeech

Related papers

• Pushing The Limits Of Unsupervised Unit Discovery For SSL Speech Representation (2023)6.34
• Multi-resolution Hubert: Multi-resolution Speech Self-supervised Learning With Masked Unit Prediction (2023)0.00
• Progressive Residual Extraction Based Pre-training For Speech Representation Learning (2024)0.00
• Fast-hubert: An Efficient Training Framework For Self-supervised Speech Representation Learning (2023)0.00
• Non-contrastive Self-supervised Learning For Utterance-level Information Extraction From Speech (2022)9.59
• Contentvec: An Improved Self-supervised Speech Representation By Disentangling Speakers (2022)0.00
• Weakly-supervised Speech Pre-training: A Case Study On Target Speech Recognition (2023)8.09
• Efficient Infusion Of Self-supervised Representations In Automatic Speech Recognition (2024)0.00