Skip to content

Opening book details…

Can I read AE-Flow: Autoencoder Normalizing Flow on EtoBox?

AE-Flow: Autoencoder Normalizing Flow by Jakub Mosiński; Piotr Biliński; Thomas Merritt; Abdelhamid Ezzerg; Daniel Korzekwa is a scholarly article available to read on EtoBox.

What is AE-Flow: Autoencoder Normalizing Flow about?

Recently normalizing flows have been gaining traction in text-tospeech (TTS) and voice conversion (VC) due to their state-of-the-art (SOTA) performance. Normalizing flows are unsupervised generative models. In this paper, we introduce supervision to the training process of normalizing flows, without the need for parallel data. We call this training paradigm AutoEncoder Normalizing Flow (AE-Flow). It adds a reconstruction loss forcing the model to use information from the conditioning to reconstruct an audio sample. Our goal is to understand the impact of each component and find the right combination of the negative log-likelihood (NLL) and the reconstruction loss in training normalizing flows with coupling blocks. For that reason we will compare flow-based mapping model trained with: (i) NLL loss, (ii) NLL and reconstruction losses, as well as (iii) reconstruction loss only. Additionally, we compare our model with SOTA VC baseline. The models are evaluated in terms of naturalness, speaker similarity, intelligibility in many-to-many and many-to-any VC settings. The results show that the proposed training paradigm systematically improves speaker similarity and naturalness when compar

Author
Jakub Mosiński; Piotr Biliński; Thomas Merritt; Abdelhamid Ezzerg; Daniel Korzekwa
Publisher
IEEE
Published
2023
Language
EN

More by Jakub Mosiński; Piotr Biliński; Thomas Merritt; Abdelhamid Ezzerg; Daniel Korzekwa

Browse all works by Jakub Mosiński; Piotr Biliński; Thomas Merritt; Abdelhamid Ezzerg; Daniel Korzekwa