---
_id: '29304'
abstract:
- lang: eng
  text: 'In this work we address disentanglement of style and content in speech signals.
    We propose a fully convolutional variational autoencoder employing two encoders:
    a content encoder and a style encoder. To foster disentanglement, we propose adversarial
    contrastive predictive coding. This new disentanglement method does neither need
    parallel data nor any supervision. We show that the proposed technique is capable
    of separating speaker and content traits into the two different representations
    and show competitive speaker-content disentanglement performance compared to other
    unsupervised approaches. We further demonstrate an increased robustness of the
    content representation against a train-test mismatch compared to spectral features,
    when used for phone recognition.'
author:
- first_name: Janek
  full_name: Ebbers, Janek
  id: '34851'
  last_name: Ebbers
- first_name: Michael
  full_name: Kuhlmann, Michael
  id: '49871'
  last_name: Kuhlmann
- first_name: Tobias
  full_name: Cord-Landwehr, Tobias
  id: '44393'
  last_name: Cord-Landwehr
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: 'Ebbers J, Kuhlmann M, Cord-Landwehr T, Haeb-Umbach R. Contrastive Predictive
    Coding Supported Factorized Variational Autoencoder for Unsupervised Learning
    of Disentangled Speech Representations. In: <i>Proceedings of the IEEE International
    Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. ; 2021:3860–3864.'
  apa: Ebbers, J., Kuhlmann, M., Cord-Landwehr, T., &#38; Haeb-Umbach, R. (2021).
    Contrastive Predictive Coding Supported Factorized Variational Autoencoder for
    Unsupervised Learning of Disentangled Speech Representations. <i>Proceedings of
    the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>,
    3860–3864.
  bibtex: '@inproceedings{Ebbers_Kuhlmann_Cord-Landwehr_Haeb-Umbach_2021, title={Contrastive
    Predictive Coding Supported Factorized Variational Autoencoder for Unsupervised
    Learning of Disentangled Speech Representations}, booktitle={Proceedings of the
    IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
    author={Ebbers, Janek and Kuhlmann, Michael and Cord-Landwehr, Tobias and Haeb-Umbach,
    Reinhold}, year={2021}, pages={3860–3864} }'
  chicago: Ebbers, Janek, Michael Kuhlmann, Tobias Cord-Landwehr, and Reinhold Haeb-Umbach.
    “Contrastive Predictive Coding Supported Factorized Variational Autoencoder for
    Unsupervised Learning of Disentangled Speech Representations.” In <i>Proceedings
    of the IEEE International Conference on Acoustics, Speech and Signal Processing
    (ICASSP)</i>, 3860–3864, 2021.
  ieee: J. Ebbers, M. Kuhlmann, T. Cord-Landwehr, and R. Haeb-Umbach, “Contrastive
    Predictive Coding Supported Factorized Variational Autoencoder for Unsupervised
    Learning of Disentangled Speech Representations,” in <i>Proceedings of the IEEE
    International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>,
    2021, pp. 3860–3864.
  mla: Ebbers, Janek, et al. “Contrastive Predictive Coding Supported Factorized Variational
    Autoencoder for Unsupervised Learning of Disentangled Speech Representations.”
    <i>Proceedings of the IEEE International Conference on Acoustics, Speech and Signal
    Processing (ICASSP)</i>, 2021, pp. 3860–3864.
  short: 'J. Ebbers, M. Kuhlmann, T. Cord-Landwehr, R. Haeb-Umbach, in: Proceedings
    of the IEEE International Conference on Acoustics, Speech and Signal Processing
    (ICASSP), 2021, pp. 3860–3864.'
date_created: 2022-01-13T07:55:29Z
date_updated: 2023-11-22T08:29:42Z
ddc:
- '000'
department:
- _id: '54'
file:
- access_level: open_access
  content_type: application/pdf
  creator: ebbers
  date_created: 2022-01-13T07:56:30Z
  date_updated: 2022-01-13T08:19:19Z
  file_id: '29305'
  file_name: Template.pdf
  file_size: 236628
  relation: main_file
file_date_updated: 2022-01-13T08:19:19Z
has_accepted_license: '1'
language:
- iso: eng
oa: '1'
page: 3860–3864
project:
- _id: '52'
  name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing'
publication: Proceedings of the IEEE International Conference on Acoustics, Speech
  and Signal Processing (ICASSP)
quality_controlled: '1'
status: public
title: Contrastive Predictive Coding Supported Factorized Variational Autoencoder
  for Unsupervised Learning of Disentangled Speech Representations
type: conference
user_id: '34851'
year: '2021'
...