Diffusion-based speech enhancement with a weighted generative-supervised learning loss - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2024

Diffusion-based speech enhancement with a weighted generative-supervised learning loss

Abstract

Diffusion-based generative models have recently gained attention in speech enhancement (SE), providing an alternative to conventional supervised methods. These models transform clean speech training samples into Gaussian noise centered at noisy speech, and subsequently learn a parameterized model to reverse this process, conditionally on noisy speech. Unlike supervised methods, generative-based SE approaches usually rely solely on an unsupervised loss, which may result in less efficient incorporation of conditioned noisy speech. To address this issue, we propose augmenting the original diffusion training objective with a mean squared error (MSE) loss, measuring the discrepancy between estimated enhanced speech and ground-truth clean speech at each reverse process iteration. Experimental results demonstrate the effectiveness of our proposed methodology.
Fichier principal
Vignette du fichier
AYILO_AVDiffSE_ICASSP24.pdf (225.26 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04210729 , version 1 (19-09-2023)
hal-04210729 , version 2 (19-01-2024)

Licence

Identifiers

Cite

Jean-Eudes Ayilo, Mostafa Sadeghi, Romain Serizel. Diffusion-based speech enhancement with a weighted generative-supervised learning loss. International Conference on Acoustics Speech and Signal Processing (ICASSP), IEEE, Apr 2024, Seoul (Korea), South Korea. ⟨10.48550/arXiv.2309.10457⟩. ⟨hal-04210729v2⟩
122 View
189 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More