Papers › TUNet: A Block-online Bandwidth Extension Model based on Transformers and...

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

26 Oct 2021arXiv:2110.13492archive 2025-07-28

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

nxtproduct/tunet officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Audio Super-ResolutionBandwidth ExtensionSensitivity

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Audio Super-Resolution VCTK Multi-Speaker TUNet + MSM pre-training Log-Spectral Distance 1.28 #3 of 7 Archive leaderboard report
Audio Super-Resolution VCTK Multi-Speaker TUNet Log-Spectral Distance 1.36 #4 of 7 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections