TUNet: A Block-online Bandwidth Extension Model based on Transformers and Self-supervised Pretraining

26 Oct 2021  ·  Viet-Anh Nguyen, Anh H. T. Nguyen, Andy W. H. Khong ·

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.

PDF Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Audio Super-Resolution VCTK Multi-Speaker TUNet + MSM pre-training Log-Spectral Distance 1.28 # 2
Audio Super-Resolution VCTK Multi-Speaker TUNet Log-Spectral Distance 1.36 # 3

Methods


No methods listed for this paper. Add relevant methods here