ATST: Audio Representation Learning with Teacher-Student Transformer

Abstract

Self-supervised learning (SSL) learns knowledge from a large amount of unlabeled data, and then transfers the knowledge to a specific problem with a limited number of labeled data. SSL has achieved promising results in various domains. This work addresses the problem of segment-level general audio SSL, and proposes a new transformer-based teacher-student SSL model, named ATST. A transformer encoder is developed on a recently emerged teacher-student baseline scheme, which largely improves the modeling capability of pre-training. In addition, a new strategy for positive pair creation is designed to fully leverage the capability of transformer. Extensive experiments have been conducted, and the proposed model achieves the new state-of-the-art results on almost all of the downstream tasks.

arXiv commentINTERSPEECH2022(Accepted)

References in corpus (9)

• Decoupled Weight Decay Regularization
• Representation Learning with Contrastive Predictive Coding
• Bootstrap your own latent: A new approach to self-supervised Learning
• VoxCeleb: a large-scale speaker identification dataset
• Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition
• Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders
• Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders
• TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech
• Towards Learning a Universal Non-Semantic Representation of Speech

Cited by in corpus (2)

• ASiT: Local-Global Audio Spectrogram vIsion Transformer for Event Classification
• Hierarchical Label Propagation: A Model-Size-Dependent Performance Booster for AudioSet Tagging