Posterior sampling algorithms for unsupervised speech enhancement with recurrent variational autoencoder - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2024

Posterior sampling algorithms for unsupervised speech enhancement with recurrent variational autoencoder

Abstract

In this paper, we address the unsupervised speech enhancement problem based on recurrent variational autoencoder (RVAE). This approach offers promising generalization performance over the supervised counterpart. Nevertheless, the involved iterative variational expectation-maximization (VEM) process at test time, which relies on a variational inference method, results in high computational complexity. To tackle this issue, we present efficient sampling techniques based on Langevin dynamics and Metropolis-Hasting algorithms, adapted to the EM-based speech enhancement with RVAE. By directly sampling from the intractable posterior distribution within the EM process, we circumvent the intricacies of variational inference. We conduct a series of experiments, comparing the proposed methods with VEM and a state-of-the-art supervised speech enhancement approach based on diffusion models. The results reveal that our sampling-based algorithms significantly outperform VEM, not only in terms of computational efficiency but also in overall performance. Furthermore, when compared to the supervised baseline, our methods showcase robust generalization performance in mismatched test conditions.
Fichier principal
Vignette du fichier
EfficientVAE_SE_ICASSP24.pdf (241.71 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04210679 , version 1 (19-09-2023)
hal-04210679 , version 2 (19-01-2024)

Licence

Identifiers

Cite

Mostafa Sadeghi, Romain Serizel. Posterior sampling algorithms for unsupervised speech enhancement with recurrent variational autoencoder. International Conference on Acoustics Speech and Signal Processing (ICASSP), IEEE, Apr 2024, Seoul (Korea), South Korea. ⟨10.48550/arXiv.2309.10439⟩. ⟨hal-04210679v2⟩
102 View
40 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More