ASAICLLGSDJan 7, 2024

EAT: Self-Supervised Pre-Training with Efficient Audio Transformer

arXiv:2401.03497v197 citationsh-index: 28IJCAI
AI Analysis

This addresses efficiency barriers for researchers and practitioners applying audio SSL models, though it is incremental as it builds on existing methods like data2vec 2.0 and Audio-MAE.

The paper tackles the high computational cost of audio self-supervised learning pre-training by introducing Efficient Audio Transformer (EAT), which achieves state-of-the-art performance on tasks like AudioSet and ESC-50 with a pre-training speedup of up to ~15x.

Audio self-supervised learning (SSL) pre-training, which aims to learn good representations from unlabeled audio, has made remarkable progress. However, the extensive computational demands during pre-training pose a significant barrier to the potential application and optimization of audio SSL models. In this paper, inspired by the success of data2vec 2.0 in image modality and Audio-MAE in audio modality, we introduce Efficient Audio Transformer (EAT) to further improve the effectiveness and efficiency in audio SSL. The proposed EAT adopts the bootstrap self-supervised training paradigm to the audio domain. A novel Utterance-Frame Objective (UFO) is designed to enhance the modeling capability of acoustic events. Furthermore, we reveal that the masking strategy is critical in audio SSL pre-training, and superior audio representations can be obtained with large inverse block masks. Experiment results demonstrate that EAT achieves state-of-the-art (SOTA) performance on a range of audio-related tasks, including AudioSet (AS-2M, AS-20K), ESC-50, and SPC-2, along with a significant pre-training speedup up to ~15x compared to existing audio SSL models.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes