# On Filter Generalization for Music Bandwidth Extension Using Deep Neural Networks

arXiv: https://arxiv.org/abs/2011.07274 · HTML: https://mlsanity.com/paper/2011.07274/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Nov 2020.

## Built on by (most cited first, 10 of 10)

- [Solving Audio Inverse Problems with a Diffusion Model](https://mlsanity.com/paper/2210.15228/) (2022)
- [HiFi++: a Unified Framework for Bandwidth Extension and Speech Enhancement](https://mlsanity.com/paper/2203.13086/) (2022)
- [Blind Audio Bandwidth Extension: A Diffusion-Based Zero-Shot Approach](https://mlsanity.com/paper/2306.01433/) (2023)
- [Catch-A-Waveform: Learning to Generate Audio from a Single Short Example](https://mlsanity.com/paper/2106.06426/) (2021)
- [Symbolic music generation conditioned on continuous-valued emotions](https://mlsanity.com/paper/2203.16165/) (2022)
- [TUNet: A Block-online Bandwidth Extension Model based on Transformers and Self-supervised Pretraining](https://mlsanity.com/paper/2110.13492/) (2021)
- [Music Separation Enhancement with Generative Modeling](https://mlsanity.com/paper/2208.12387/) (2022)
- [High-Resolution Speech Restoration with Latent Diffusion Model](https://mlsanity.com/paper/2409.11145/) (2024)
- [Audio Spectral Enhancement: Leveraging Autoencoders for Low Latency Reconstruction of Long, Lossy Audio Sequences](https://mlsanity.com/paper/2108.03703/) (2021)
- [Should All Noises Be Treated Equally: Impact of Input Noise Variability on Neural Network Robustness](https://mlsanity.com/paper/2609.14504/) (2026)

## Abstract (arXiv)

In this paper, we address a sub-topic of the broad domain of audio enhancement, namely musical audio bandwidth extension. We formulate the bandwidth extension problem using deep neural networks, where a band-limited signal is provided as input to the network, with the goal of reconstructing a full-bandwidth output. Our main contribution centers on the impact of the choice of low pass filter when training and subsequently testing the network. For two different state of the art deep architectures, ResNet and U-Net, we demonstrate that when the training and testing filters are matched, improvements in signal-to-noise ratio (SNR) of up to 7dB can be obtained. However, when these filters differ, the improvement falls considerably and under some training conditions results in a lower SNR than the band-limited input. To circumvent this apparent overfitting to filter shape, we propose a data augmentation strategy which utilizes multiple low pass filters during training and leads to improved generalization to unseen filtering conditions at test time.