---
_id: '15237'
abstract:
- lang: eng
text: This paper presents an approach to voice conversion, whichdoes neither
require parallel data nor speaker or phone labels fortraining. It can convert
between speakers which are not in thetraining set by employing the previously
proposed concept of afactorized hierarchical variational autoencoder. Here, linguisticand
speaker induced variations are separated upon the notionthat content induced variations
change at a much shorter timescale, i.e., at the segment level, than speaker induced
variations,which vary at the longer utterance level. In this contribution wepropose
to employ convolutional instead of recurrent networklayers in the encoder and decoder blocks, which is shown toachieve
better phone recognition accuracy on the latent segmentvariables at frame-level
due to their better temporal resolution.For voice conversion the mean of the utterance
variables is re-placed with the respective estimated mean of the target speaker.The
resulting log-mel spectra of the decoder output are used aslocal conditions of
a WaveNet which is utilized for synthesis ofthe speech waveforms. Experiments
show both good disentan-glement properties of the latent space variables, and
good voiceconversion performance.
author:
- first_name: Tobias
full_name: Gburrek, Tobias
id: '44006'
last_name: Gburrek
- first_name: Thomas
full_name: Glarner, Thomas
id: '14169'
last_name: Glarner
- 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
- first_name: Petra
full_name: Wagner, Petra
last_name: Wagner
citation:
ama: 'Gburrek T, Glarner T, Ebbers J, Haeb-Umbach R, Wagner P. Unsupervised Learning
of a Disentangled Speech Representation for Voice Conversion. In: Proc. 10th
ISCA Speech Synthesis Workshop. ; 2019:81-86. doi:10.21437/SSW.2019-15'
apa: Gburrek, T., Glarner, T., Ebbers, J., Haeb-Umbach, R., & Wagner, P. (2019).
Unsupervised Learning of a Disentangled Speech Representation for Voice Conversion.
Proc. 10th ISCA Speech Synthesis Workshop, 81–86. https://doi.org/10.21437/SSW.2019-15
bibtex: '@inproceedings{Gburrek_Glarner_Ebbers_Haeb-Umbach_Wagner_2019, title={Unsupervised
Learning of a Disentangled Speech Representation for Voice Conversion}, DOI={10.21437/SSW.2019-15}, booktitle={Proc.
10th ISCA Speech Synthesis Workshop}, author={Gburrek, Tobias and Glarner, Thomas
and Ebbers, Janek and Haeb-Umbach, Reinhold and Wagner, Petra}, year={2019}, pages={81–86}
}'
chicago: Gburrek, Tobias, Thomas Glarner, Janek Ebbers, Reinhold Haeb-Umbach, and
Petra Wagner. “Unsupervised Learning of a Disentangled Speech Representation for
Voice Conversion.” In Proc. 10th ISCA Speech Synthesis Workshop, 81–86,
2019. https://doi.org/10.21437/SSW.2019-15.
ieee: 'T. Gburrek, T. Glarner, J. Ebbers, R. Haeb-Umbach, and P. Wagner, “Unsupervised
Learning of a Disentangled Speech Representation for Voice Conversion,” in Proc.
10th ISCA Speech Synthesis Workshop, Vienna, 2019, pp. 81–86, doi: 10.21437/SSW.2019-15.'
mla: Gburrek, Tobias, et al. “Unsupervised Learning of a Disentangled Speech Representation
for Voice Conversion.” Proc. 10th ISCA Speech Synthesis Workshop, 2019,
pp. 81–86, doi:10.21437/SSW.2019-15.
short: 'T. Gburrek, T. Glarner, J. Ebbers, R. Haeb-Umbach, P. Wagner, in: Proc.
10th ISCA Speech Synthesis Workshop, 2019, pp. 81–86.'
conference:
location: Vienna
name: 10th ISCA Speech Synthesis Workshop
date_created: 2019-12-04T08:12:29Z
date_updated: 2023-11-17T06:20:39Z
department:
- _id: '54'
doi: 10.21437/SSW.2019-15
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://www.isca-speech.org/archive/pdfs/ssw_2019/gburrek19_ssw.pdf
oa: '1'
page: 81-86
publication: Proc. 10th ISCA Speech Synthesis Workshop
quality_controlled: '1'
related_material:
link:
- description: Listening examples
relation: supplementary_material
url: http://go.upb.de/vcex
status: public
title: Unsupervised Learning of a Disentangled Speech Representation for Voice Conversion
type: conference
user_id: '44006'
year: '2019'
...
---
_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: INTERSPEECH
2018, Hyderabad, India. ; 2018.'
apa: Glarner, T., Hanebrink, P., Ebbers, J., & Haeb-Umbach, R. (2018). Full
Bayesian Hidden Markov Model Variational Autoencoder for Acoustic Unit Discovery.
INTERSPEECH 2018, Hyderabad, India.
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 INTERSPEECH 2018, Hyderabad, India, 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.” INTERSPEECH 2018, Hyderabad, India, 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'
...
---
_id: '11770'
abstract:
- lang: eng
text: 'In this contribution we show how to exploit text data to support word discovery
from audio input in an underresourced target language. Given audio, of which a
certain amount is transcribed at the word level, and additional unrelated text
data, the approach is able to learn a probabilistic mapping from acoustic units
to characters and utilize it to segment the audio data into words without the
need of a pronunciation dictionary. This is achieved by three components: an unsupervised
acoustic unit discovery system, a supervisedly trained acoustic unit-to-grapheme
converter, and a word discovery system, which is initialized with a language model
trained on the text data. Experiments for multiple setups show that the initialization
of the language model with text data improves the word segementation performance
by a large margin.'
author:
- first_name: Thomas
full_name: Glarner, Thomas
id: '14169'
last_name: Glarner
- first_name: Benedikt
full_name: Boenninghoff, Benedikt
last_name: Boenninghoff
- first_name: Oliver
full_name: Walter, Oliver
last_name: Walter
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Glarner T, Boenninghoff B, Walter O, Haeb-Umbach R. Leveraging Text Data for
Word Segmentation for Underresourced Languages. In: INTERSPEECH 2017, Stockholm,
Schweden. ; 2017.'
apa: Glarner, T., Boenninghoff, B., Walter, O., & Haeb-Umbach, R. (2017). Leveraging
Text Data for Word Segmentation for Underresourced Languages. In INTERSPEECH
2017, Stockholm, Schweden.
bibtex: '@inproceedings{Glarner_Boenninghoff_Walter_Haeb-Umbach_2017, title={Leveraging
Text Data for Word Segmentation for Underresourced Languages}, booktitle={INTERSPEECH
2017, Stockholm, Schweden}, author={Glarner, Thomas and Boenninghoff, Benedikt
and Walter, Oliver and Haeb-Umbach, Reinhold}, year={2017} }'
chicago: Glarner, Thomas, Benedikt Boenninghoff, Oliver Walter, and Reinhold Haeb-Umbach.
“Leveraging Text Data for Word Segmentation for Underresourced Languages.” In
INTERSPEECH 2017, Stockholm, Schweden, 2017.
ieee: T. Glarner, B. Boenninghoff, O. Walter, and R. Haeb-Umbach, “Leveraging Text
Data for Word Segmentation for Underresourced Languages,” in INTERSPEECH 2017,
Stockholm, Schweden, 2017.
mla: Glarner, Thomas, et al. “Leveraging Text Data for Word Segmentation for Underresourced
Languages.” INTERSPEECH 2017, Stockholm, Schweden, 2017.
short: 'T. Glarner, B. Boenninghoff, O. Walter, R. Haeb-Umbach, in: INTERSPEECH
2017, Stockholm, Schweden, 2017.'
date_created: 2019-07-12T05:27:55Z
date_updated: 2022-01-06T06:51:08Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/2017/INTERSPEECH_2017_Glarner_paper.pdf
oa: '1'
publication: INTERSPEECH 2017, Stockholm, Schweden
related_material:
link:
- description: Poster
relation: supplementary_material
url: https://groups.uni-paderborn.de/nt/pubs/2017/INTERSPEECH_2017_Glarner_poster.pdf
status: public
title: Leveraging Text Data for Word Segmentation for Underresourced Languages
type: conference
user_id: '44006'
year: '2017'
...
---
_id: '11759'
abstract:
- lang: eng
text: 'Variational Autoencoders (VAEs) have been shown to provide efficient neural-network-based
approximate Bayesian inference for observation models for which exact inference
is intractable. Its extension, the so-called Structured VAE (SVAE) allows inference
in the presence of both discrete and continuous latent variables. Inspired by
this extension, we developed a VAE with Hidden Markov Models (HMMs) as latent
models. We applied the resulting HMM-VAE to the task of acoustic unit discovery
in a zero resource scenario. Starting from an initial model based on variational
inference in an HMM with Gaussian Mixture Model (GMM) emission probabilities,
the accuracy of the acoustic unit discovery could be significantly improved by
the HMM-VAE. In doing so we were able to demonstrate for an unsupervised learning
task what is well-known in the supervised learning case: Neural networks provide
superior modeling power compared to GMMs.'
author:
- first_name: Janek
full_name: Ebbers, Janek
id: '34851'
last_name: Ebbers
- first_name: Jahn
full_name: Heymann, Jahn
id: '9168'
last_name: Heymann
- first_name: Lukas
full_name: Drude, Lukas
id: '11213'
last_name: Drude
- first_name: Thomas
full_name: Glarner, Thomas
id: '14169'
last_name: Glarner
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
- first_name: Bhiksha
full_name: Raj, Bhiksha
last_name: Raj
citation:
ama: 'Ebbers J, Heymann J, Drude L, Glarner T, Haeb-Umbach R, Raj B. Hidden Markov
Model Variational Autoencoder for Acoustic Unit Discovery. In: INTERSPEECH
2017, Stockholm, Schweden. ; 2017.'
apa: Ebbers, J., Heymann, J., Drude, L., Glarner, T., Haeb-Umbach, R., & Raj,
B. (2017). Hidden Markov Model Variational Autoencoder for Acoustic Unit Discovery.
INTERSPEECH 2017, Stockholm, Schweden.
bibtex: '@inproceedings{Ebbers_Heymann_Drude_Glarner_Haeb-Umbach_Raj_2017, title={Hidden
Markov Model Variational Autoencoder for Acoustic Unit Discovery}, booktitle={INTERSPEECH
2017, Stockholm, Schweden}, author={Ebbers, Janek and Heymann, Jahn and Drude,
Lukas and Glarner, Thomas and Haeb-Umbach, Reinhold and Raj, Bhiksha}, year={2017}
}'
chicago: Ebbers, Janek, Jahn Heymann, Lukas Drude, Thomas Glarner, Reinhold Haeb-Umbach,
and Bhiksha Raj. “Hidden Markov Model Variational Autoencoder for Acoustic Unit
Discovery.” In INTERSPEECH 2017, Stockholm, Schweden, 2017.
ieee: J. Ebbers, J. Heymann, L. Drude, T. Glarner, R. Haeb-Umbach, and B. Raj, “Hidden
Markov Model Variational Autoencoder for Acoustic Unit Discovery,” 2017.
mla: Ebbers, Janek, et al. “Hidden Markov Model Variational Autoencoder for Acoustic
Unit Discovery.” INTERSPEECH 2017, Stockholm, Schweden, 2017.
short: 'J. Ebbers, J. Heymann, L. Drude, T. Glarner, R. Haeb-Umbach, B. Raj, in:
INTERSPEECH 2017, Stockholm, Schweden, 2017.'
date_created: 2019-07-12T05:27:42Z
date_updated: 2023-11-22T08:29:06Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/2017/INTERSPEECH_2017_Ebbers_paper.pdf
oa: '1'
publication: INTERSPEECH 2017, Stockholm, Schweden
quality_controlled: '1'
related_material:
link:
- description: Poster
relation: supplementary_material
url: https://groups.uni-paderborn.de/nt/pubs/2017/INTERSPEECH_2017_Ebbers_poster.pdf
- description: Slides
relation: supplementary_material
url: https://groups.uni-paderborn.de/nt/pubs/2017/INTERSPEECH_2017_Ebbers_slides.pdf
status: public
title: Hidden Markov Model Variational Autoencoder for Acoustic Unit Discovery
type: conference
user_id: '34851'
year: '2017'
...
---
_id: '11771'
abstract:
- lang: eng
text: This paper is concerned with speech presence probability estimation employing
an explicit model of the temporal and spectral correlations of speech. An undirected
graphical model is introduced, based on a Factor Graph formulation. It is shown
that this undirected model cures some of the theoretical issues of an earlier
directed graphical model. Furthermore, we formulate a message passing inference
scheme based on an approximate graph factorization, identify this inference scheme
as a particular message passing schedule based on the turbo principle and suggest
further alternative schedules. The experiments show an improved performance over
speech presence probability estimation based on an IID assumption, and a slightly
better performance of the turbo schedule over the alternatives.
author:
- first_name: Thomas
full_name: Glarner, Thomas
id: '14169'
last_name: Glarner
- first_name: Mohammad
full_name: Mahdi Momenzadeh, Mohammad
last_name: Mahdi Momenzadeh
- first_name: Lukas
full_name: Drude, Lukas
id: '11213'
last_name: Drude
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Glarner T, Mahdi Momenzadeh M, Drude L, Haeb-Umbach R. Factor Graph Decoding
for Speech Presence Probability Estimation. In: 12. ITG Fachtagung Sprachkommunikation
(ITG 2016). ; 2016.'
apa: Glarner, T., Mahdi Momenzadeh, M., Drude, L., & Haeb-Umbach, R. (2016).
Factor Graph Decoding for Speech Presence Probability Estimation. In 12. ITG
Fachtagung Sprachkommunikation (ITG 2016).
bibtex: '@inproceedings{Glarner_Mahdi Momenzadeh_Drude_Haeb-Umbach_2016, title={Factor
Graph Decoding for Speech Presence Probability Estimation}, booktitle={12. ITG
Fachtagung Sprachkommunikation (ITG 2016)}, author={Glarner, Thomas and Mahdi
Momenzadeh, Mohammad and Drude, Lukas and Haeb-Umbach, Reinhold}, year={2016}
}'
chicago: Glarner, Thomas, Mohammad Mahdi Momenzadeh, Lukas Drude, and Reinhold Haeb-Umbach.
“Factor Graph Decoding for Speech Presence Probability Estimation.” In 12.
ITG Fachtagung Sprachkommunikation (ITG 2016), 2016.
ieee: T. Glarner, M. Mahdi Momenzadeh, L. Drude, and R. Haeb-Umbach, “Factor Graph
Decoding for Speech Presence Probability Estimation,” in 12. ITG Fachtagung
Sprachkommunikation (ITG 2016), 2016.
mla: Glarner, Thomas, et al. “Factor Graph Decoding for Speech Presence Probability
Estimation.” 12. ITG Fachtagung Sprachkommunikation (ITG 2016), 2016.
short: 'T. Glarner, M. Mahdi Momenzadeh, L. Drude, R. Haeb-Umbach, in: 12. ITG Fachtagung
Sprachkommunikation (ITG 2016), 2016.'
date_created: 2019-07-12T05:27:56Z
date_updated: 2022-01-06T06:51:08Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/2016/itgspeech2016_08_Glarner.pdf
oa: '1'
publication: 12. ITG Fachtagung Sprachkommunikation (ITG 2016)
related_material:
link:
- description: Slides
relation: supplementary_material
url: https://groups.uni-paderborn.de/nt/pubs/2016/itgspeech2016_08_Glarner_slides.pdf
status: public
title: Factor Graph Decoding for Speech Presence Probability Estimation
type: conference
user_id: '44006'
year: '2016'
...