Skip to Main content Skip to Navigation
Conference papers

A Benchmark of Dynamical Variational Autoencoders applied to Speech Spectrogram Modeling

Abstract : The Variational Autoencoder (VAE) is a powerful deep generative model that is now extensively used to represent high-dimensional complex data via a low-dimensional latent space learned in an unsupervised manner. In the original VAE model, input data vectors are processed independently. In recent years, a series of papers have presented different extensions of the VAE to process sequential data, that not only model the latent space, but also model the temporal dependencies within a sequence of data vectors and corresponding latent vectors, relying on recurrent neural networks. We recently performed a comprehensive review of those models and unified them into a general class called Dynamical Variational Autoencoders (DVAEs). In the present paper, we present the results of an experimental benchmark comparing six of those DVAE models on the speech analysis-resynthesis task, as an illustration of the high potential of DVAEs for speech modeling.
Complete list of metadata
Contributor : Xavier Alameda-Pineda Connect in order to contact the contributor
Submitted on : Tuesday, January 18, 2022 - 4:56:19 PM
Last modification on : Wednesday, May 4, 2022 - 12:00:02 PM


Files produced by the author(s)



Xiaoyu Bie, Laurent Girin, Simon Leglaive, Thomas Hueber, Xavier Alameda-Pineda. A Benchmark of Dynamical Variational Autoencoders applied to Speech Spectrogram Modeling. Interspeech 2021 - 22nd Annual Conference of the International Speech Communication Association, Aug 2021, Brno, Czech Republic. pp.46-50, ⟨10.21437/Interspeech.2021-256⟩. ⟨hal-03295657⟩



Record views


Files downloads