Tunet: A Block-Online Bandwidth Extension Model Based On Transformers And Self-Supervised Pretraining
TL
TL;DR
A block-online variant of the temporal feature-wise linear modulation (TFiLM) model to achieve bandwidth extension that simplifies the UNet backbone of the TFiLM to reduce inference time and employs an efficient transformer at the bottleneck to alleviate performance degradation.
Abstract
We introduce a block-online variant of the temporal feature-wise linear modulation (TFiLM) model to achieve bandwidth extension. The proposed architecture simplifies the UNet backbone of the TFiLM to reduce inference time and employs an efficient transformer at the bottleneck to alleviate performance degradation. We also utilize self-supervised pretraining and data augmentation to enhance the quality of bandwidth extended signals and reduce the sensitivity with respect to downsampling methods. Experiment results on the VCTK dataset show that the proposed method outperforms several recent baselines in both intrusive and non-intrusive metrics. Pretraining and filter augmentation also help stabilize and enhance the overall performance.
References23 items
1
WSRGlow: A Glow-based Waveform Generative Model for Audio Super-Resolution
2
NU-Wave: A Diffusion Probabilistic Model for Neural Audio Upsampling
3
On Filter Generalization for Music Bandwidth Extension Using Deep Neural Networks
4
Dnsmos: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressors
5