---
_id: '11907'
abstract:
- lang: eng
  text: The invention of the Variational Autoencoder enables the application of Neural
    Networks to a wide range of tasks in unsupervised learning, including the field
    of Acoustic Unit Discovery (AUD). The recently proposed Hidden Markov Model Variational
    Autoencoder (HMMVAE) allows a joint training of a neural network based feature
    extractor and a structured prior for the latent space given by a Hidden Markov
    Model. It has been shown that the HMMVAE significantly outperforms pure GMM-HMM
    based systems on the AUD task. However, the HMMVAE cannot autonomously infer the
    number of acoustic units and thus relies on the GMM-HMM system for initialization.
    This paper introduces the Bayesian Hidden Markov Model Variational Autoencoder
    (BHMMVAE) which solves these issues by embedding the HMMVAE in a Bayesian framework
    with a Dirichlet Process Prior for the distribution of the acoustic units, and
    diagonal or full-covariance Gaussians as emission distributions. Experiments on
    TIMIT and Xitsonga show that the BHMMVAE is able to autonomously infer a reasonable
    number of acoustic units, can be initialized without supervision by a GMM-HMM
    system, achieves computationally efficient stochastic variational inference by
    using natural gradient descent, and, additionally, improves the AUD performance
    over the HMMVAE.
author:
- first_name: Thomas
  full_name: Glarner, Thomas
  id: '14169'
  last_name: Glarner
- first_name: Patrick
  full_name: Hanebrink, Patrick
  last_name: Hanebrink
- first_name: Janek
  full_name: Ebbers, Janek
  id: '34851'
  last_name: Ebbers
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: 'Glarner T, Hanebrink P, Ebbers J, Haeb-Umbach R. Full Bayesian Hidden Markov
    Model Variational Autoencoder for Acoustic Unit Discovery. In: <i>INTERSPEECH
    2018, Hyderabad, India</i>. ; 2018.'
  apa: Glarner, T., Hanebrink, P., Ebbers, J., &#38; Haeb-Umbach, R. (2018). Full
    Bayesian Hidden Markov Model Variational Autoencoder for Acoustic Unit Discovery.
    <i>INTERSPEECH 2018, Hyderabad, India</i>.
  bibtex: '@inproceedings{Glarner_Hanebrink_Ebbers_Haeb-Umbach_2018, title={Full Bayesian
    Hidden Markov Model Variational Autoencoder for Acoustic Unit Discovery}, booktitle={INTERSPEECH
    2018, Hyderabad, India}, author={Glarner, Thomas and Hanebrink, Patrick and Ebbers,
    Janek and Haeb-Umbach, Reinhold}, year={2018} }'
  chicago: Glarner, Thomas, Patrick Hanebrink, Janek Ebbers, and Reinhold Haeb-Umbach.
    “Full Bayesian Hidden Markov Model Variational Autoencoder for Acoustic Unit Discovery.”
    In <i>INTERSPEECH 2018, Hyderabad, India</i>, 2018.
  ieee: T. Glarner, P. Hanebrink, J. Ebbers, and R. Haeb-Umbach, “Full Bayesian Hidden
    Markov Model Variational Autoencoder for Acoustic Unit Discovery,” 2018.
  mla: Glarner, Thomas, et al. “Full Bayesian Hidden Markov Model Variational Autoencoder
    for Acoustic Unit Discovery.” <i>INTERSPEECH 2018, Hyderabad, India</i>, 2018.
  short: 'T. Glarner, P. Hanebrink, J. Ebbers, R. Haeb-Umbach, in: INTERSPEECH 2018,
    Hyderabad, India, 2018.'
date_created: 2019-07-12T05:30:34Z
date_updated: 2023-11-22T08:29:22Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://groups.uni-paderborn.de/nt/pubs/2018/INTERSPEECH_2018_Glarner_Paper.pdf
oa: '1'
publication: INTERSPEECH 2018, Hyderabad, India
quality_controlled: '1'
related_material:
  link:
  - description: Slides
    relation: supplementary_material
    url: https://groups.uni-paderborn.de/nt/pubs/2018/INTERSPEECH_2018_Glarner_Slides.pdf
status: public
title: Full Bayesian Hidden Markov Model Variational Autoencoder for Acoustic Unit
  Discovery
type: conference
user_id: '34851'
year: '2018'
...