Sparsity-based audio declip** methods: Selected overview, new algorithms, and large-scale evaluation

C Gaultier, S Kitić, R Gribonval… - IEEE/ACM Transactions …, 2021 - ieeexplore.ieee.org
Recent advances in audio declip** have substantially improved the state of the art. Yet,
practitioners need guidelines to choose a method, and while existing benchmarks have …

Miipher: A robust speech restoration model integrating self-supervised speech and text representations

Y Koizumi, H Zen, S Karita, Y Ding… - … IEEE Workshop on …, 2023 - ieeexplore.ieee.org
Speech restoration (SR) is a task of converting degraded speech signals into high-quality
ones. In this study, we propose a robust SR model called Miipher, and apply Miipher to a …

BEHM-GAN: Bandwidth extension of historical music using generative adversarial networks

E Moliner, V Välimäki - IEEE/ACM Transactions on Audio …, 2022 - ieeexplore.ieee.org
Audio bandwidth extension aims to expand the spectrum of bandlimited audio signals.
Although this topic has been broadly studied during recent years, the particular problem of …

General purpose audio effect removal

M Rice, CJ Steinmetz, G Fazekas… - 2023 IEEE Workshop …, 2023 - ieeexplore.ieee.org
Although the design and application of audio effects is well understood, the inverse problem
of removing these effects is significantly more challenging and far less studied. Recently …

Vrdmg: Vocal restoration via diffusion posterior sampling with multiple guidance

C Hernandez-Olivan, K Saito, N Murata… - ICASSP 2024-2024 …, 2024 - ieeexplore.ieee.org
Restoring degraded music signals is essential to enhance audio quality for downstream
music manipulation. Recent diffusion-based music restoration methods have demonstrated …

Cascaded time+ time-frequency unet for speech enhancement: Jointly addressing clip**, codec distortions, and gaps

AA Nair, K Koishida - ICASSP 2021-2021 IEEE International …, 2021 - ieeexplore.ieee.org
Speech enhancement aims to improve speech quality by eliminating noise and distortions.
While most speech enhancement methods address signal independent additive sources of …