no code implementations • 7 May 2024 • Eloi Moliner, Jean-Marie Lemercier, Simon Welker, Timo Gerkmann, Vesa Välimäki
In this paper, we present an unsupervised single-channel method for joint blind dereverberation and room impulse response estimation, based on posterior sampling with diffusion models.
1 code implementation • 27 Mar 2024 • Eloi Moliner, Maija Turunen, Filip Elvander, Vesa Välimäki
This paper presents a novel approach to audio restoration, focusing on the enhancement of low-quality music recordings, and in particular historical ones.
no code implementations • 15 Feb 2024 • Jean-Marie Lemercier, Julius Richter, Simon Welker, Eloi Moliner, Vesa Välimäki, Timo Gerkmann
Here, we aim to show that diffusion models can combine the best of both worlds and offer the opportunity to design audio restoration algorithms with a good degree of interpretability and a remarkable performance in terms of sound quality.
no code implementations • 22 Dec 2023 • Eloi Moliner, Leonardo Fierro, Alec Wright, Matti Hämäläinen, Vesa Välimäki
This letter introduces an innovative method to enhance the quality of audio time stretching by precisely decomposing a sound into sines, transients, and noise and by improving the processing of the latter component.
no code implementations • 2 Jun 2023 • Eloi Moliner, Filip Elvander, Vesa Välimäki
In cases where the lowpass degradation is unknown, such as in restoring historical audio recordings, this becomes a blind problem.
no code implementations • 26 May 2023 • Otto Mikkonen, Alec Wright, Eloi Moliner, Vesa Välimäki
The sound of magnetic recording media, such as open-reel and cassette tape recorders, is still sought after by today's sound practitioners due to the imperfections embedded in the physics of the magnetic recording process.
1 code implementation • 24 May 2023 • Eloi Moliner, Vesa Välimäki
The proposed method uses an unconditionally trained generative model, which can be conditioned in a zero-shot fashion for audio inpainting, and is able to regenerate gaps of any size.
1 code implementation • 27 Oct 2022 • Eloi Moliner, Jaakko Lehtinen, Vesa Välimäki
This paper presents CQT-Diff, a data-driven generative audio model that can, once trained, be used for solving various different audio inverse problems in a problem-agnostic setting.
1 code implementation • 13 Jun 2022 • Eloi Moliner, Vesa Välimäki
A diffusion probabilistic model is applied to generate highly realistic quasiperiodic noises.
1 code implementation • 13 Apr 2022 • Eloi Moliner, Vesa Välimäki
Audio bandwidth extension aims to expand the spectrum of narrow-band audio signals.
no code implementations • 17 Feb 2022 • Eloi Moliner, Vesa Välimäki
Enhancing the sound quality of historical music recordings is a long-standing problem.