Self-Attention for Audio Super-Resolution

2021/08/26 by Rakotonirina, Nathanaël Carraz · 1 citation
#Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Sound (cs.SD) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2108.11637

Abstract

Convolutions operate only locally, thus failing to model global interactions. Self-attention is, however, able to learn representations that capture long-range dependencies in sequences. We propose a network architecture for audio super-resolution that combines convolution and self-attention. Attention-based Feature-Wise Linear Modulation (AFiLM) uses self-attention mechanism instead of recurrent neural networks to modulate the activations of the convolutional model. Extensive experiments show that our model outperforms existing approaches on standard benchmarks. Moreover, it allows for more parallelization resulting in significantly faster training.

Cited by

• A Practical Approach to Power Saving in Hearables Using Sub-Nyquist Sampling with Bandwidth Extension

Related

• Memory Controlled Sequential Self Attention for Sound Recognition
• Learning Continuous Representation of Audio for Arbitrary Scale Super Resolution
• Attention is All You Need? Good Embeddings with Statistics are enough:Large Scale Audio Understanding without Transformers/ Convolutions/ BERTs/ Mixers/ Attention/ RNNs or ....
• Assessment of Self-Attention on Learned Features For Sound Event Localization and Detection
• AEROMamba: An efficient architecture for audio super-resolution using generative adversarial networks and state space models