StoRM: A diffusion-based stochastic regeneration model for speech enhancement and dereverberation

JM Lemercier, J Richter, S Welker… - … /ACM Transactions on …, 2023 - ieeexplore.ieee.org
Diffusion models have shown a great ability at bridging the performance gap between
predictive and generative approaches for speech enhancement. We have shown that they …

Causal diffusion models for generalized speech enhancement

J Richter, S Welker, JM Lemercier, B Lay… - IEEE Open Journal …, 2024 - ieeexplore.ieee.org
In this work, we present a causal speech enhancement system that is designed to handle
different types of corruptions. This paper is an extended version of our contribution to the …

ICASSP 2023 speech signal improvement challenge

R Cutler, A Saabas, B Naderi, NC Ristea… - IEEE Open Journal …, 2024 - ieeexplore.ieee.org
The ICASSP 2023 Speech Signal Improvement Challenge is intended to stimulate research
in the area of improving the speech signal quality in communication systems. The speech …

Diffusion-based generative modeling with discriminative guidance for streamable speech enhancement

C Li, S Cornell, S Watanabe… - 2024 IEEE Spoken …, 2024 - ieeexplore.ieee.org
Diffusion-based generative models (DGMs) have recently attracted attention in speech
enhancement (SE) research as previous works showed a remarkable generalization …

A Maximum Entropy Information Bottleneck (MEIB) Regularization for Generative Speech Enhancement with HiFi-GAN

M Sach, J Pirklbauer, K Fluyt, W Tirry… - … ; 15th ITG Conference, 2023 - ieeexplore.ieee.org
Generative approaches to speech enhancement using a vocoder to synthesize a clean
speech estimate aim at solving the problem of residual noise occuring with typical …