Paper ID | AUD-1.5 | ||
Paper Title | ATTENTION IS ALL YOU NEED IN SPEECH SEPARATION | ||
Authors | Cem Subakan, Mirco Ravanelli, Mila, Canada; Samuele Cornell, Università Politecnica delle Marche (IT), Italy; Mirko Bronzi, Mila, Canada; Jianyuan Zhong, University of Rochester, United States | ||
Session | AUD-1: Audio and Speech Source Separation 1: Speech Separation | ||
Location | Gather.Town | ||
Session Time: | Tuesday, 08 June, 13:00 - 13:45 | ||
Presentation Time: | Tuesday, 08 June, 13:00 - 13:45 | ||
Presentation | Poster | ||
Topic | Audio and Acoustic Signal Processing: [AUD-SEP] Audio and Speech Source Separation | ||
IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
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. |