Attention is All You Need in Speech Separation

Code

• github.com/speechbrain/speechbrain/tree/develop/recipes/WSJ0Mix/separation
  Officialpytorch★ 0
• github.com/Zhongyang-debug/Attention-Is-All-You-Need-In-Speech-Separation
  pytorch★ 80
• github.com/SungFeng-Huang/SSL-pretraining-separation
  pytorch★ 63
• github.com/2024-MindSpore-1/Code3/tree/main/Sepformer
  mindspore★ 0

Abstract

Recurrent Neural Networks (RNNs) have long been the dominant architecture in sequence-to-sequence learning. RNNs, however, are inherently sequential models that do not allow parallelization of their computations. Transformers are emerging as a natural alternative to standard RNNs, replacing recurrent computations with a multi-head attention mechanism. In this paper, we propose the SepFormer, a novel RNN-free Transformer-based neural network for speech separation. The SepFormer learns short and long-term dependencies with a multi-scale approach that employs transformers. The proposed model achieves state-of-the-art (SOTA) performance on the standard WSJ0-2/3mix datasets. It reaches an SI-SNRi of 22.3 dB on WSJ0-2mix and an SI-SNRi of 19.5 dB on WSJ0-3mix. The SepFormer inherits the parallelization advantages of Transformers and achieves a competitive performance even when downsampling the encoded representation by a factor of 8. It is thus significantly faster and it is less memory-demanding than the latest speech separation systems with comparable performance.

Tasks

Benchmark Results

Reproductions