English

A Benchmark of Dynamical Variational Autoencoders applied to Speech Spectrogram Modeling

Sound 2021-06-15 v2 Audio and Speech Processing

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.

Keywords

Cite

@article{arxiv.2106.06500,
  title  = {A Benchmark of Dynamical Variational Autoencoders applied to Speech Spectrogram Modeling},
  author = {Xiaoyu Bie and Laurent Girin and Simon Leglaive and Thomas Hueber and Xavier Alameda-Pineda},
  journal= {arXiv preprint arXiv:2106.06500},
  year   = {2021}
}

Comments

Accepted to Interspeech 2021. arXiv admin note: text overlap with arXiv:2008.12595

R2 v1 2026-06-24T03:06:37.109Z