2020/04/06 by Andis Draguns, Emīls Ozoliņš, Draguns, Andis +7 · 1 citation
Computer Science · #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Music and Audio Processing #Neural Networks and Applications #Sound (cs.SD) #Speech Recognition and Synthesis #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2004.04662
openalex publication_date 2020/04/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Attention is a commonly used mechanism in sequence processing, but it is of O(n2) complexity which prevents its application to long sequences. The recently introduced neural Shuffle-Exchange network offers a computation-efficient alternative, enabling the modelling of long-range dependencies in O(n log n) time. The model, however, is quite complex, involving a sophisticated gating mechanism derived from the Gated Recurrent Unit. In this paper, we present a simple and lightweight variant of the Shuffle-Exchange network, which is based on a residual network employing GELU and Layer Normalization. The proposed architecture not only scales to longer sequences but also converges faster and provides better accuracy. It surpasses the Shuffle-Exchange network on the LAMBADA language modelling task and achieves state-of-the-art performance on the MusicNet dataset for music transcription while being efficient in the number of parameters. We show how to combine the improved Shuffle-Exchange network with convolutional layers, establishing it as a useful building block in long sequence processing applications.