2021
DOI: 10.48550/arxiv.2110.13492
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

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

Viet-Anh Nguyen,
Anh H. T. Nguyen,
Andy W. H. Khong

Abstract: We introduce a block-online variant of the temporal featurewise 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 result… Show more

Help me understand this report
View published versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
2

Citation Types

0
2
0

Year Published

2022
2022
2023
2023

Publication Types

Select...
1
1

Relationship

0
2

Authors

Journals

citations
Cited by 2 publications
(2 citation statements)
references
References 10 publications
0
2
0
Order By: Relevance
“…Li et al [14] also experimented with using variable-band filters with randomized cutoff frequencies to increase the robustness of the model in real-life speech bandwidth-extension scenarios. Similarly, Nguyen et al [43] applied anti-aliasing filters having random order and ripple intending to improve the robustness of their model.…”
Section: Lowpass Filter Generalizationmentioning
confidence: 99%
“…Li et al [14] also experimented with using variable-band filters with randomized cutoff frequencies to increase the robustness of the model in real-life speech bandwidth-extension scenarios. Similarly, Nguyen et al [43] applied anti-aliasing filters having random order and ripple intending to improve the robustness of their model.…”
Section: Lowpass Filter Generalizationmentioning
confidence: 99%
“…Li et al [14] also experimented with using variable-band filters with randomized cutoff frequencies to increase the robustness of the model in real-life speech bandwidth-extension scenarios. Similarly, Nguyen et al [42] applied anti-aliasing filters having random order and ripple intending to improve the robustness of their model.…”
Section: Lowpass Filter Generalizationmentioning
confidence: 99%