---
_id: '44849'
author:
- first_name: Frederik
full_name: Rautenberg, Frederik
id: '72602'
last_name: Rautenberg
- first_name: Michael
full_name: Kuhlmann, Michael
id: '49871'
last_name: Kuhlmann
- first_name: Janek
full_name: Ebbers, Janek
id: '34851'
last_name: Ebbers
- first_name: Jana
full_name: Wiechmann, Jana
last_name: Wiechmann
- first_name: Fritz
full_name: Seebauer, Fritz
last_name: Seebauer
- first_name: Petra
full_name: Wagner, Petra
last_name: Wagner
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Rautenberg F, Kuhlmann M, Ebbers J, et al. Speech Disentanglement for Analysis
and Modification of Acoustic and Perceptual Speaker Characteristics. In: Fortschritte
Der Akustik - DAGA 2023. ; 2023:1409-1412.'
apa: Rautenberg, F., Kuhlmann, M., Ebbers, J., Wiechmann, J., Seebauer, F., Wagner,
P., & Haeb-Umbach, R. (2023). Speech Disentanglement for Analysis and Modification
of Acoustic and Perceptual Speaker Characteristics. Fortschritte Der Akustik
- DAGA 2023, 1409–1412.
bibtex: '@inproceedings{Rautenberg_Kuhlmann_Ebbers_Wiechmann_Seebauer_Wagner_Haeb-Umbach_2023,
title={Speech Disentanglement for Analysis and Modification of Acoustic and Perceptual
Speaker Characteristics}, booktitle={Fortschritte der Akustik - DAGA 2023}, author={Rautenberg,
Frederik and Kuhlmann, Michael and Ebbers, Janek and Wiechmann, Jana and Seebauer,
Fritz and Wagner, Petra and Haeb-Umbach, Reinhold}, year={2023}, pages={1409–1412}
}'
chicago: Rautenberg, Frederik, Michael Kuhlmann, Janek Ebbers, Jana Wiechmann, Fritz
Seebauer, Petra Wagner, and Reinhold Haeb-Umbach. “Speech Disentanglement for
Analysis and Modification of Acoustic and Perceptual Speaker Characteristics.”
In Fortschritte Der Akustik - DAGA 2023, 1409–12, 2023.
ieee: F. Rautenberg et al., “Speech Disentanglement for Analysis and Modification
of Acoustic and Perceptual Speaker Characteristics,” in Fortschritte der Akustik
- DAGA 2023, Hamburg, 2023, pp. 1409–1412.
mla: Rautenberg, Frederik, et al. “Speech Disentanglement for Analysis and Modification
of Acoustic and Perceptual Speaker Characteristics.” Fortschritte Der Akustik
- DAGA 2023, 2023, pp. 1409–12.
short: 'F. Rautenberg, M. Kuhlmann, J. Ebbers, J. Wiechmann, F. Seebauer, P. Wagner,
R. Haeb-Umbach, in: Fortschritte Der Akustik - DAGA 2023, 2023, pp. 1409–1412.'
conference:
end_date: 2023-03-09
location: Hamburg
name: DAGA 2023 - 49. Jahrestagung für Akustik
start_date: 2023-03-06
date_created: 2023-05-15T08:48:54Z
date_updated: 2024-02-29T17:05:16Z
ddc:
- '000'
department:
- _id: '54'
- _id: '660'
file:
- access_level: open_access
content_type: application/pdf
creator: frra
date_created: 2024-02-29T16:15:12Z
date_updated: 2024-02-29T16:15:12Z
file_id: '52221'
file_name: Daga_2023_Rautenberg_Paper.pdf
file_size: 289493
relation: main_file
file_date_updated: 2024-02-29T16:15:12Z
has_accepted_license: '1'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://pub.dega-akustik.de/DAGA_2023/data/articles/000105.pdf
oa: '1'
page: 1409-1412
project:
- _id: '129'
grant_number: '438445824'
name: 'TRR 318 - C06: TRR 318 - Technisch unterstütztes Erklären von Stimmcharakteristika
(Teilprojekt C06)'
publication: Fortschritte der Akustik - DAGA 2023
publication_status: published
status: public
title: Speech Disentanglement for Analysis and Modification of Acoustic and Perceptual
Speaker Characteristics
type: conference
user_id: '72602'
year: '2023'
...
---
_id: '49111'
abstract:
- lang: eng
text: Due to the high variation in the application requirements of sound event detection
(SED) systems, it is not sufficient to evaluate systems only in a single operating
mode. Therefore, the community recently adopted the polyphonic sound detection
score (PSDS) as an evaluation metric, which is the normalized area under the PSD
receiver operating characteristic (PSD-ROC). It summarizes the system performance
over a range of operating modes resulting from varying the decision threshold
that is used to translate the system output scores into a binary detection output.
Hence, it provides a more complete picture of the overall system behavior and
is less biased by specific threshold tuning. However, besides the decision threshold
there is also the post-processing that can be changed to enter another operating
mode. In this paper we propose the post-processing independent PSDS (piPSDS) as
a generalization of the PSDS. Here, the post-processing independent PSD-ROC includes
operating points from varying post-processings with varying decision thresholds.
Thus, it summarizes even more operating modes of an SED system and allows for
system comparison without the need of implementing a post-processing and without
a bias due to different post-processings. While piPSDS can in principle combine
different types of post-processing, we here, as a first step, present median filter
independent PSDS (miPSDS) results for this year’s DCASE Challenge Task4a systems.
Source code is publicly available in our sed_scores_eval package (https://github.com/fgnt/sed_scores_eval).
author:
- 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: Romain
full_name: Serizel, Romain
last_name: Serizel
citation:
ama: 'Ebbers J, Haeb-Umbach R, Serizel R. Post-Processing Independent Evaluation
of Sound Event Detection Systems. In: Proceedings of the 8th Detection and
Classification of Acoustic Scenes and Events 2023 Workshop (DCASE2023). ;
2023:36–40.'
apa: Ebbers, J., Haeb-Umbach, R., & Serizel, R. (2023). Post-Processing Independent
Evaluation of Sound Event Detection Systems. Proceedings of the 8th Detection
and Classification of Acoustic Scenes and Events 2023 Workshop (DCASE2023),
36–40.
bibtex: '@inproceedings{Ebbers_Haeb-Umbach_Serizel_2023, place={Tampere, Finland},
title={Post-Processing Independent Evaluation of Sound Event Detection Systems},
booktitle={Proceedings of the 8th Detection and Classification of Acoustic Scenes
and Events 2023 Workshop (DCASE2023)}, author={Ebbers, Janek and Haeb-Umbach,
Reinhold and Serizel, Romain}, year={2023}, pages={36–40} }'
chicago: Ebbers, Janek, Reinhold Haeb-Umbach, and Romain Serizel. “Post-Processing
Independent Evaluation of Sound Event Detection Systems.” In Proceedings of
the 8th Detection and Classification of Acoustic Scenes and Events 2023 Workshop
(DCASE2023), 36–40. Tampere, Finland, 2023.
ieee: J. Ebbers, R. Haeb-Umbach, and R. Serizel, “Post-Processing Independent Evaluation
of Sound Event Detection Systems,” in Proceedings of the 8th Detection and
Classification of Acoustic Scenes and Events 2023 Workshop (DCASE2023), 2023,
pp. 36–40.
mla: Ebbers, Janek, et al. “Post-Processing Independent Evaluation of Sound Event
Detection Systems.” Proceedings of the 8th Detection and Classification of
Acoustic Scenes and Events 2023 Workshop (DCASE2023), 2023, pp. 36–40.
short: 'J. Ebbers, R. Haeb-Umbach, R. Serizel, in: Proceedings of the 8th Detection
and Classification of Acoustic Scenes and Events 2023 Workshop (DCASE2023), Tampere,
Finland, 2023, pp. 36–40.'
date_created: 2023-11-22T08:20:26Z
date_updated: 2024-11-15T20:34:18Z
ddc:
- '000'
department:
- _id: '54'
file:
- access_level: closed
content_type: application/pdf
creator: ebbers
date_created: 2023-11-22T08:25:08Z
date_updated: 2023-11-22T08:25:08Z
file_id: '49112'
file_name: dcase2023_ebbers.pdf
file_size: 221875
relation: main_file
success: 1
file_date_updated: 2023-11-22T08:25:08Z
has_accepted_license: '1'
language:
- iso: eng
page: 36–40
place: Tampere, Finland
project:
- _id: '52'
name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing'
publication: Proceedings of the 8th Detection and Classification of Acoustic Scenes
and Events 2023 Workshop (DCASE2023)
quality_controlled: '1'
status: public
title: Post-Processing Independent Evaluation of Sound Event Detection Systems
type: conference
user_id: '34851'
year: '2023'
...
---
_id: '33857'
author:
- first_name: Michael
full_name: Kuhlmann, Michael
id: '49871'
last_name: Kuhlmann
- first_name: Fritz
full_name: Seebauer, Fritz
last_name: Seebauer
- first_name: Janek
full_name: Ebbers, Janek
id: '34851'
last_name: Ebbers
- first_name: Petra
full_name: Wagner, Petra
last_name: Wagner
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Kuhlmann M, Seebauer F, Ebbers J, Wagner P, Haeb-Umbach R. Investigation into
Target Speaking Rate Adaptation for Voice Conversion. In: Interspeech 2022.
ISCA; 2022. doi:10.21437/interspeech.2022-10740'
apa: Kuhlmann, M., Seebauer, F., Ebbers, J., Wagner, P., & Haeb-Umbach, R. (2022).
Investigation into Target Speaking Rate Adaptation for Voice Conversion. Interspeech
2022. https://doi.org/10.21437/interspeech.2022-10740
bibtex: '@inproceedings{Kuhlmann_Seebauer_Ebbers_Wagner_Haeb-Umbach_2022, title={Investigation
into Target Speaking Rate Adaptation for Voice Conversion}, DOI={10.21437/interspeech.2022-10740},
booktitle={Interspeech 2022}, publisher={ISCA}, author={Kuhlmann, Michael and
Seebauer, Fritz and Ebbers, Janek and Wagner, Petra and Haeb-Umbach, Reinhold},
year={2022} }'
chicago: Kuhlmann, Michael, Fritz Seebauer, Janek Ebbers, Petra Wagner, and Reinhold
Haeb-Umbach. “Investigation into Target Speaking Rate Adaptation for Voice Conversion.”
In Interspeech 2022. ISCA, 2022. https://doi.org/10.21437/interspeech.2022-10740.
ieee: 'M. Kuhlmann, F. Seebauer, J. Ebbers, P. Wagner, and R. Haeb-Umbach, “Investigation
into Target Speaking Rate Adaptation for Voice Conversion,” 2022, doi: 10.21437/interspeech.2022-10740.'
mla: Kuhlmann, Michael, et al. “Investigation into Target Speaking Rate Adaptation
for Voice Conversion.” Interspeech 2022, ISCA, 2022, doi:10.21437/interspeech.2022-10740.
short: 'M. Kuhlmann, F. Seebauer, J. Ebbers, P. Wagner, R. Haeb-Umbach, in: Interspeech
2022, ISCA, 2022.'
date_created: 2022-10-21T06:50:59Z
date_updated: 2023-10-25T09:04:45Z
ddc:
- '000'
department:
- _id: '54'
doi: 10.21437/interspeech.2022-10740
file:
- access_level: closed
content_type: application/pdf
creator: mikuhl
date_created: 2023-07-15T16:16:12Z
date_updated: 2023-07-15T16:16:12Z
file_id: '46070'
file_name: kuhlmann22_interspeech.pdf
file_size: 303863
relation: main_file
success: 1
file_date_updated: 2023-07-15T16:16:12Z
has_accepted_license: '1'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://www.isca-speech.org/archive/pdfs/interspeech_2022/kuhlmann22_interspeech.pdf
oa: '1'
project:
- _id: '52'
name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing'
publication: Interspeech 2022
publication_status: published
publisher: ISCA
quality_controlled: '1'
status: public
title: Investigation into Target Speaking Rate Adaptation for Voice Conversion
type: conference
user_id: '34851'
year: '2022'
...
---
_id: '34072'
abstract:
- lang: eng
text: "Performing an adequate evaluation of sound event detection (SED) systems
is far from trivial and is still subject to ongoing research. The recently proposed
polyphonic sound detection (PSD)-receiver operating characteristic (ROC) and PSD
score (PSDS) make an important step into the direction of an evaluation of SED
systems which is independent from a certain decision threshold. This allows to
obtain a more complete picture of the overall system behavior which is less biased
by threshold tuning. Yet, the PSD-ROC is currently only approximated using a finite
set of thresholds. The choice of\r\nthe thresholds used in approximation, however,
can have a severe impact on the resulting PSDS. In this paper we propose a method
which allows for computing system performance on an evaluation set for all possible
thresholds jointly, enabling accurate computation not only of the PSD-ROC and
PSDS but also of other collar-based\r\nand intersection-based performance curves.
It further allows to select the threshold which best fulfills the requirements
of a given application. Source code is publicly available in our SED evaluation
package sed_scores_eval."
author:
- 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: Romain
full_name: Serizel, Romain
last_name: Serizel
citation:
ama: 'Ebbers J, Haeb-Umbach R, Serizel R. Threshold Independent Evaluation of Sound
Event Detection Scores. In: Proceedings of the IEEE International Conference
on Acoustics, Speech and Signal Processing (ICASSP). ; 2022.'
apa: Ebbers, J., Haeb-Umbach, R., & Serizel, R. (2022). Threshold Independent
Evaluation of Sound Event Detection Scores. Proceedings of the IEEE International
Conference on Acoustics, Speech and Signal Processing (ICASSP).
bibtex: '@inproceedings{Ebbers_Haeb-Umbach_Serizel_2022, title={Threshold Independent
Evaluation of Sound Event Detection Scores}, booktitle={Proceedings of the IEEE
International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
author={Ebbers, Janek and Haeb-Umbach, Reinhold and Serizel, Romain}, year={2022}
}'
chicago: Ebbers, Janek, Reinhold Haeb-Umbach, and Romain Serizel. “Threshold Independent
Evaluation of Sound Event Detection Scores.” In Proceedings of the IEEE International
Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022.
ieee: J. Ebbers, R. Haeb-Umbach, and R. Serizel, “Threshold Independent Evaluation
of Sound Event Detection Scores,” 2022.
mla: Ebbers, Janek, et al. “Threshold Independent Evaluation of Sound Event Detection
Scores.” Proceedings of the IEEE International Conference on Acoustics, Speech
and Signal Processing (ICASSP), 2022.
short: 'J. Ebbers, R. Haeb-Umbach, R. Serizel, in: Proceedings of the IEEE International
Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022.'
date_created: 2022-11-14T12:17:03Z
date_updated: 2023-11-22T08:26:58Z
ddc:
- '000'
department:
- _id: '54'
file:
- access_level: open_access
content_type: application/pdf
creator: ebbers
date_created: 2022-11-14T12:19:55Z
date_updated: 2022-11-14T12:19:55Z
file_id: '34073'
file_name: Template.pdf
file_size: 214001
relation: main_file
file_date_updated: 2022-11-14T12:19:55Z
has_accepted_license: '1'
language:
- iso: eng
oa: '1'
publication: Proceedings of the IEEE International Conference on Acoustics, Speech
and Signal Processing (ICASSP)
quality_controlled: '1'
status: public
title: Threshold Independent Evaluation of Sound Event Detection Scores
type: conference
user_id: '34851'
year: '2022'
...
---
_id: '49113'
abstract:
- lang: eng
text: 'In this report we present our system for the Detection and Classification
of Acoustic Scenes and Events (DCASE) 2022 Challenge Task 4: Sound Event Detection
in Domestic Environments 1 . As in previous editions of the Challenge, we use
forward-backward convolutional recurrent neural networks (FBCRNNs) [1, 2] for
weakly labeled and semi-supervised sound event detection (SED) and eventually
generate strong pseudo labels for weakly labeled and unlabeled data. Then, (tag-conditioned)
bidirectional CRNNs (Bi-CRNNs) [1, 2] are trained in a strongly supervised manner
as our final SED models. In each of the training stages we use multiple iterations
of self-training. Compared to previous editions, we improved our system performance
by 1) some tweaks regarding data augmentation, pseudo labeling and inference 2)
using weakly labeled AudioSet data [3] for pretraining larger networks and 3)
augmenting the DESED data [4] with strongly labeled AudioSet data [5] for finetuning
of the networks. Source code is publicly available at https://github.com/fgnt/pb_sed.'
author:
- 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: Ebbers J, Haeb-Umbach R. Pre-Training And Self-Training For Sound Event
Detection In Domestic Environments.; 2022.
apa: Ebbers, J., & Haeb-Umbach, R. (2022). Pre-Training And Self-Training
For Sound Event Detection In Domestic Environments.
bibtex: '@book{Ebbers_Haeb-Umbach_2022, title={Pre-Training And Self-Training For
Sound Event Detection In Domestic Environments}, author={Ebbers, Janek and Haeb-Umbach,
Reinhold}, year={2022} }'
chicago: Ebbers, Janek, and Reinhold Haeb-Umbach. Pre-Training And Self-Training
For Sound Event Detection In Domestic Environments, 2022.
ieee: J. Ebbers and R. Haeb-Umbach, Pre-Training And Self-Training For Sound
Event Detection In Domestic Environments. 2022.
mla: Ebbers, Janek, and Reinhold Haeb-Umbach. Pre-Training And Self-Training
For Sound Event Detection In Domestic Environments. 2022.
short: J. Ebbers, R. Haeb-Umbach, Pre-Training And Self-Training For Sound Event
Detection In Domestic Environments, 2022.
date_created: 2023-11-22T08:34:23Z
date_updated: 2024-11-15T20:34:52Z
ddc:
- '000'
department:
- _id: '54'
file:
- access_level: closed
content_type: application/pdf
creator: ebbers
date_created: 2023-11-22T08:35:23Z
date_updated: 2023-11-22T08:35:23Z
file_id: '49114'
file_name: dcase2022_tech_report_ebbers.pdf
file_size: 491650
relation: main_file
success: 1
file_date_updated: 2023-11-22T08:35:23Z
has_accepted_license: '1'
language:
- iso: eng
project:
- _id: '52'
name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing'
status: public
title: Pre-Training And Self-Training For Sound Event Detection In Domestic Environments
type: report
user_id: '34851'
year: '2022'
...
---
_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: Proceedings of the IEEE International
Conference on Acoustics, Speech and Signal Processing (ICASSP). ; 2021:3860–3864.'
apa: Ebbers, J., Kuhlmann, M., Cord-Landwehr, T., & Haeb-Umbach, R. (2021).
Contrastive Predictive Coding Supported Factorized Variational Autoencoder for
Unsupervised Learning of Disentangled Speech Representations. Proceedings of
the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),
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 Proceedings
of the IEEE International Conference on Acoustics, Speech and Signal Processing
(ICASSP), 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 Proceedings of the IEEE
International Conference on Acoustics, Speech and Signal Processing (ICASSP),
2021, pp. 3860–3864.
mla: Ebbers, Janek, et al. “Contrastive Predictive Coding Supported Factorized Variational
Autoencoder for Unsupervised Learning of Disentangled Speech Representations.”
Proceedings of the IEEE International Conference on Acoustics, Speech and Signal
Processing (ICASSP), 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'
...
---
_id: '29308'
abstract:
- lang: eng
text: 'In this paper we present our system for the Detection and Classification
of Acoustic Scenes and Events (DCASE) 2021 Challenge Task 4: Sound Event Detection
and Separation in Domestic Environments, where it scored the fourth rank. Our
presented solution is an advancement of our system used in the previous edition
of the task.We use a forward-backward convolutional recurrent neural network (FBCRNN)
for tagging and pseudo labeling followed by tag-conditioned sound event detection
(SED) models which are trained using strong pseudo labels provided by the FBCRNN.
Our advancement over our earlier model is threefold. First, we introduce a strong
label loss in the objective of the FBCRNN to take advantage of the strongly labeled
synthetic data during training. Second, we perform multiple iterations of self-training
for both the FBCRNN and tag-conditioned SED models. Third, while we used only
tag-conditioned CNNs as our SED model in the previous edition we here explore
sophisticated tag-conditioned SED model architectures, namely, bidirectional CRNNs
and bidirectional convolutional transformer neural networks (CTNNs), and combine
them. With metric and class specific tuning of median filter lengths for post-processing,
our final SED model, consisting of 6 submodels (2 of each architecture), achieves
on the public evaluation set poly-phonic sound event detection scores (PSDS) of
0.455 for scenario 1 and 0.684 for scenario as well as a collar-based F1-score
of 0.596 outperforming the baselines and our model from the previous edition by
far. Source code is publicly available at https://github.com/fgnt/pb_sed.'
author:
- 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: 'Ebbers J, Haeb-Umbach R. Self-Trained Audio Tagging and Sound Event Detection
in Domestic Environments. In: Proceedings of the 6th Detection and Classification
of Acoustic Scenes and Events 2021 Workshop (DCASE2021). ; 2021:226–230.'
apa: Ebbers, J., & Haeb-Umbach, R. (2021). Self-Trained Audio Tagging and Sound
Event Detection in Domestic Environments. Proceedings of the 6th Detection
and Classification of Acoustic Scenes and Events 2021 Workshop (DCASE2021),
226–230.
bibtex: '@inproceedings{Ebbers_Haeb-Umbach_2021, place={Barcelona, Spain}, title={Self-Trained
Audio Tagging and Sound Event Detection in Domestic Environments}, booktitle={Proceedings
of the 6th Detection and Classification of Acoustic Scenes and Events 2021 Workshop
(DCASE2021)}, author={Ebbers, Janek and Haeb-Umbach, Reinhold}, year={2021}, pages={226–230}
}'
chicago: Ebbers, Janek, and Reinhold Haeb-Umbach. “Self-Trained Audio Tagging and
Sound Event Detection in Domestic Environments.” In Proceedings of the 6th
Detection and Classification of Acoustic Scenes and Events 2021 Workshop (DCASE2021),
226–230. Barcelona, Spain, 2021.
ieee: J. Ebbers and R. Haeb-Umbach, “Self-Trained Audio Tagging and Sound Event
Detection in Domestic Environments,” in Proceedings of the 6th Detection and
Classification of Acoustic Scenes and Events 2021 Workshop (DCASE2021), 2021,
pp. 226–230.
mla: Ebbers, Janek, and Reinhold Haeb-Umbach. “Self-Trained Audio Tagging and Sound
Event Detection in Domestic Environments.” Proceedings of the 6th Detection
and Classification of Acoustic Scenes and Events 2021 Workshop (DCASE2021),
2021, pp. 226–230.
short: 'J. Ebbers, R. Haeb-Umbach, in: Proceedings of the 6th Detection and Classification
of Acoustic Scenes and Events 2021 Workshop (DCASE2021), Barcelona, Spain, 2021,
pp. 226–230.'
date_created: 2022-01-13T08:07:47Z
date_updated: 2023-11-22T08:28:32Z
ddc:
- '000'
department:
- _id: '54'
file:
- access_level: open_access
content_type: application/pdf
creator: ebbers
date_created: 2022-01-13T08:08:54Z
date_updated: 2022-01-13T08:19:50Z
file_id: '29309'
file_name: template.pdf
file_size: 239462
relation: main_file
file_date_updated: 2022-01-13T08:19:50Z
has_accepted_license: '1'
language:
- iso: eng
oa: '1'
page: 226–230
place: Barcelona, Spain
project:
- _id: '52'
name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing'
publication: Proceedings of the 6th Detection and Classification of Acoustic Scenes
and Events 2021 Workshop (DCASE2021)
publication_identifier:
isbn:
- 978-84-09-36072-7
quality_controlled: '1'
status: public
title: Self-Trained Audio Tagging and Sound Event Detection in Domestic Environments
type: conference
user_id: '34851'
year: '2021'
...
---
_id: '29306'
abstract:
- lang: eng
text: Recently, there has been a rising interest in sound recognition via Acoustic
Sensor Networks to support applications such as ambient assisted living or environmental
habitat monitoring. With state-of-the-art sound recognition being dominated by
deep-learning-based approaches, there is a high demand for labeled training data.
Despite the availability of large-scale data sets such as Google's AudioSet,
acquiring training data matching a certain application environment is still often
a problem. In this paper we are concerned with human activity monitoring in a
domestic environment using an ASN consisting of multiple nodes each providing
multichannel signals. We propose a self-training based domain adaptation approach,
which only requires unlabeled data from the target environment. Here, a sound
recognition system trained on AudioSet, the teacher, generates pseudo labels for
data from the target environment on which a student network is trained. The student
can furthermore glean information about the spatial arrangement of sensors and
sound sources to further improve classification performance. It is shown that the
student significantly improves recognition performance over the pre-trained teacher
without relying on labeled data from the environment the system is deployed in.
author:
- first_name: Janek
full_name: Ebbers, Janek
id: '34851'
last_name: Ebbers
- first_name: Moritz Curt
full_name: Keyser, Moritz Curt
last_name: Keyser
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Ebbers J, Keyser MC, Haeb-Umbach R. Adapting Sound Recognition to A New Environment
Via Self-Training. In: Proceedings of the 29th European Signal Processing Conference
(EUSIPCO). ; 2021:1135–1139.'
apa: Ebbers, J., Keyser, M. C., & Haeb-Umbach, R. (2021). Adapting Sound Recognition
to A New Environment Via Self-Training. Proceedings of the 29th European Signal
Processing Conference (EUSIPCO), 1135–1139.
bibtex: '@inproceedings{Ebbers_Keyser_Haeb-Umbach_2021, title={Adapting Sound Recognition
to A New Environment Via Self-Training}, booktitle={Proceedings of the 29th European
Signal Processing Conference (EUSIPCO)}, author={Ebbers, Janek and Keyser, Moritz
Curt and Haeb-Umbach, Reinhold}, year={2021}, pages={1135–1139} }'
chicago: Ebbers, Janek, Moritz Curt Keyser, and Reinhold Haeb-Umbach. “Adapting
Sound Recognition to A New Environment Via Self-Training.” In Proceedings of
the 29th European Signal Processing Conference (EUSIPCO), 1135–1139, 2021.
ieee: J. Ebbers, M. C. Keyser, and R. Haeb-Umbach, “Adapting Sound Recognition to
A New Environment Via Self-Training,” in Proceedings of the 29th European Signal
Processing Conference (EUSIPCO), 2021, pp. 1135–1139.
mla: Ebbers, Janek, et al. “Adapting Sound Recognition to A New Environment Via
Self-Training.” Proceedings of the 29th European Signal Processing Conference
(EUSIPCO), 2021, pp. 1135–1139.
short: 'J. Ebbers, M.C. Keyser, R. Haeb-Umbach, in: Proceedings of the 29th European
Signal Processing Conference (EUSIPCO), 2021, pp. 1135–1139.'
date_created: 2022-01-13T08:01:21Z
date_updated: 2023-11-22T08:28:50Z
ddc:
- '000'
department:
- _id: '54'
file:
- access_level: open_access
content_type: application/pdf
creator: ebbers
date_created: 2022-01-13T08:03:26Z
date_updated: 2022-01-13T08:19:35Z
file_id: '29307'
file_name: conference_101719.pdf
file_size: 213938
relation: main_file
file_date_updated: 2022-01-13T08:19:35Z
has_accepted_license: '1'
language:
- iso: eng
oa: '1'
page: 1135–1139
project:
- _id: '52'
name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing'
publication: Proceedings of the 29th European Signal Processing Conference (EUSIPCO)
quality_controlled: '1'
status: public
title: Adapting Sound Recognition to A New Environment Via Self-Training
type: conference
user_id: '34851'
year: '2021'
...
---
_id: '20753'
abstract:
- lang: eng
text: 'In this paper we present our system for the detection and classification
of acoustic scenes and events (DCASE) 2020 Challenge Task 4: Sound event detection
and separation in domestic environments. We introduce two new models: the forward-backward
convolutional recurrent neural network (FBCRNN) and the tag-conditioned convolutional
neural network (CNN). The FBCRNN employs two recurrent neural network (RNN) classifiers
sharing the same CNN for preprocessing. With one RNN processing a recording in
forward direction and the other in backward direction, the two networks are trained
to jointly predict audio tags, i.e., weak labels, at each time step within a recording,
given that at each time step they have jointly processed the whole recording.
The proposed training encourages the classifiers to tag events as soon as possible.
Therefore, after training, the networks can be applied to shorter audio segments
of, e.g., 200ms, allowing sound event detection (SED). Further, we propose a tag-conditioned
CNN to complement SED. It is trained to predict strong labels while using (predicted)
tags, i.e., weak labels, as additional input. For training pseudo strong labels
from a FBCRNN ensemble are used. The presented system scored the fourth and third
place in the systems and teams rankings, respectively. Subsequent improvements
allow our system to even outperform the challenge baseline and winner systems
in average by, respectively, 18.0% and 2.2% event-based F1-score on the validation
set. Source code is publicly available at https://github.com/fgnt/pb_sed.'
author:
- 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: 'Ebbers J, Haeb-Umbach R. Forward-Backward Convolutional Recurrent Neural Networks
and Tag-Conditioned Convolutional Neural Networks for Weakly Labeled Semi-Supervised
Sound Event Detection. In: Proceedings of the Detection and Classification
of Acoustic Scenes and Events 2020 Workshop (DCASE2020). ; 2020.'
apa: Ebbers, J., & Haeb-Umbach, R. (2020). Forward-Backward Convolutional Recurrent
Neural Networks and Tag-Conditioned Convolutional Neural Networks for Weakly Labeled
Semi-Supervised Sound Event Detection. Proceedings of the Detection and Classification
of Acoustic Scenes and Events 2020 Workshop (DCASE2020).
bibtex: '@inproceedings{Ebbers_Haeb-Umbach_2020, title={Forward-Backward Convolutional
Recurrent Neural Networks and Tag-Conditioned Convolutional Neural Networks for
Weakly Labeled Semi-Supervised Sound Event Detection}, booktitle={Proceedings
of the Detection and Classification of Acoustic Scenes and Events 2020 Workshop
(DCASE2020)}, author={Ebbers, Janek and Haeb-Umbach, Reinhold}, year={2020} }'
chicago: Ebbers, Janek, and Reinhold Haeb-Umbach. “Forward-Backward Convolutional
Recurrent Neural Networks and Tag-Conditioned Convolutional Neural Networks for
Weakly Labeled Semi-Supervised Sound Event Detection.” In Proceedings of the
Detection and Classification of Acoustic Scenes and Events 2020 Workshop (DCASE2020),
2020.
ieee: J. Ebbers and R. Haeb-Umbach, “Forward-Backward Convolutional Recurrent Neural
Networks and Tag-Conditioned Convolutional Neural Networks for Weakly Labeled
Semi-Supervised Sound Event Detection,” 2020.
mla: Ebbers, Janek, and Reinhold Haeb-Umbach. “Forward-Backward Convolutional Recurrent
Neural Networks and Tag-Conditioned Convolutional Neural Networks for Weakly Labeled
Semi-Supervised Sound Event Detection.” Proceedings of the Detection and Classification
of Acoustic Scenes and Events 2020 Workshop (DCASE2020), 2020.
short: 'J. Ebbers, R. Haeb-Umbach, in: Proceedings of the Detection and Classification
of Acoustic Scenes and Events 2020 Workshop (DCASE2020), 2020.'
date_created: 2020-12-16T08:55:27Z
date_updated: 2023-11-22T08:27:32Z
ddc:
- '000'
department:
- _id: '54'
file:
- access_level: open_access
content_type: application/pdf
creator: huesera
date_created: 2020-12-16T08:57:22Z
date_updated: 2020-12-16T08:57:22Z
file_id: '20754'
file_name: DCASE2020Workshop_Ebbers_Paper.pdf
file_size: 108326
relation: main_file
file_date_updated: 2020-12-16T08:57:22Z
has_accepted_license: '1'
language:
- iso: eng
license: https://creativecommons.org/publicdomain/zero/1.0/
oa: '1'
project:
- _id: '52'
name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing'
publication: Proceedings of the Detection and Classification of Acoustic Scenes and
Events 2020 Workshop (DCASE2020)
quality_controlled: '1'
status: public
title: Forward-Backward Convolutional Recurrent Neural Networks and Tag-Conditioned
Convolutional Neural Networks for Weakly Labeled Semi-Supervised Sound Event Detection
type: conference
user_id: '34851'
year: '2020'
...
---
_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: '15794'
abstract:
- lang: eng
text: In this paper we present our audio tagging system for the DCASE 2019 Challenge
Task 2. We propose a model consisting of a convolutional front end using log-mel-energies
as input features, a recurrent neural network sequence encoder and a fully connected
classifier network outputting an activity probability for each of the 80 considered
event classes. Due to the recurrent neural network, which encodes a whole sequence
into a single vector, our model is able to process sequences of varying lengths.
The model is trained with only little manually labeled training data and a larger
amount of automatically labeled web data, which hence suffers from label noise.
To efficiently train the model with the provided data we use various data augmentation
to prevent overfitting and improve generalization. Our best submitted system achieves
a label-weighted label-ranking average precision (lwlrap) of 75.5% on the private
test set which is an absolute improvement of 21.7% over the baseline. This system
scored the second place in the teams ranking of the DCASE 2019 Challenge Task
2 and the fifth place in the Kaggle competition “Freesound Audio Tagging 2019”
with more than 400 participants. After the challenge ended we further improved
performance to 76.5% lwlrap setting a new state-of-the-art on this dataset.
author:
- 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: 'Ebbers J, Haeb-Umbach R. Convolutional Recurrent Neural Network and Data Augmentation
for Audio Tagging with Noisy Labels and Minimal Supervision. In: DCASE2019
Workshop, New York, USA. ; 2019.'
apa: Ebbers, J., & Haeb-Umbach, R. (2019). Convolutional Recurrent Neural Network
and Data Augmentation for Audio Tagging with Noisy Labels and Minimal Supervision.
DCASE2019 Workshop, New York, USA.
bibtex: '@inproceedings{Ebbers_Haeb-Umbach_2019, title={Convolutional Recurrent
Neural Network and Data Augmentation for Audio Tagging with Noisy Labels and Minimal
Supervision}, booktitle={DCASE2019 Workshop, New York, USA}, author={Ebbers, Janek
and Haeb-Umbach, Reinhold}, year={2019} }'
chicago: Ebbers, Janek, and Reinhold Haeb-Umbach. “Convolutional Recurrent Neural
Network and Data Augmentation for Audio Tagging with Noisy Labels and Minimal
Supervision.” In DCASE2019 Workshop, New York, USA, 2019.
ieee: J. Ebbers and R. Haeb-Umbach, “Convolutional Recurrent Neural Network and
Data Augmentation for Audio Tagging with Noisy Labels and Minimal Supervision,”
2019.
mla: Ebbers, Janek, and Reinhold Haeb-Umbach. “Convolutional Recurrent Neural Network
and Data Augmentation for Audio Tagging with Noisy Labels and Minimal Supervision.”
DCASE2019 Workshop, New York, USA, 2019.
short: 'J. Ebbers, R. Haeb-Umbach, in: DCASE2019 Workshop, New York, USA, 2019.'
date_created: 2020-02-05T10:16:03Z
date_updated: 2023-11-22T08:30:12Z
ddc:
- '000'
department:
- _id: '54'
file:
- access_level: open_access
content_type: application/pdf
creator: huesera
date_created: 2020-02-05T10:18:06Z
date_updated: 2020-02-05T10:18:06Z
file_id: '15795'
file_name: DCASE_2019_WS_Ebbers_Paper.pdf
file_size: 184967
relation: main_file
file_date_updated: 2020-02-05T10:18:06Z
has_accepted_license: '1'
language:
- iso: eng
oa: '1'
project:
- _id: '52'
name: Computing Resources Provided by the Paderborn Center for Parallel Computing
publication: DCASE2019 Workshop, New York, USA
quality_controlled: '1'
status: public
title: Convolutional Recurrent Neural Network and Data Augmentation for Audio Tagging
with Noisy Labels and Minimal Supervision
type: conference
user_id: '34851'
year: '2019'
...
---
_id: '15796'
abstract:
- lang: eng
text: In this paper we consider human daily activity recognition using an acoustic
sensor network (ASN) which consists of nodes distributed in a home environment.
Assuming that the ASN is permanently recording, the vast majority of recordings
is silence. Therefore, we propose to employ a computationally efficient two-stage
sound recognition system, consisting of an initial sound activity detection (SAD)
and a subsequent sound event classification (SEC), which is only activated once
sound activity has been detected. We show how a low-latency activity detector
with high temporal resolution can be trained from weak labels with low temporal
resolution. We further demonstrate the advantage of using spatial features for
the subsequent event classification task.
author:
- first_name: Janek
full_name: Ebbers, Janek
id: '34851'
last_name: Ebbers
- 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
- first_name: Andreas
full_name: Brendel, Andreas
last_name: Brendel
- first_name: Walter
full_name: Kellermann, Walter
last_name: Kellermann
citation:
ama: 'Ebbers J, Drude L, Haeb-Umbach R, Brendel A, Kellermann W. Weakly Supervised
Sound Activity Detection and Event Classification in Acoustic Sensor Networks.
In: CAMSAP 2019, Guadeloupe, West Indies. ; 2019.'
apa: Ebbers, J., Drude, L., Haeb-Umbach, R., Brendel, A., & Kellermann, W. (2019).
Weakly Supervised Sound Activity Detection and Event Classification in Acoustic
Sensor Networks. CAMSAP 2019, Guadeloupe, West Indies.
bibtex: '@inproceedings{Ebbers_Drude_Haeb-Umbach_Brendel_Kellermann_2019, title={Weakly
Supervised Sound Activity Detection and Event Classification in Acoustic Sensor
Networks}, booktitle={CAMSAP 2019, Guadeloupe, West Indies}, author={Ebbers, Janek
and Drude, Lukas and Haeb-Umbach, Reinhold and Brendel, Andreas and Kellermann,
Walter}, year={2019} }'
chicago: Ebbers, Janek, Lukas Drude, Reinhold Haeb-Umbach, Andreas Brendel, and
Walter Kellermann. “Weakly Supervised Sound Activity Detection and Event Classification
in Acoustic Sensor Networks.” In CAMSAP 2019, Guadeloupe, West Indies,
2019.
ieee: J. Ebbers, L. Drude, R. Haeb-Umbach, A. Brendel, and W. Kellermann, “Weakly
Supervised Sound Activity Detection and Event Classification in Acoustic Sensor
Networks,” 2019.
mla: Ebbers, Janek, et al. “Weakly Supervised Sound Activity Detection and Event
Classification in Acoustic Sensor Networks.” CAMSAP 2019, Guadeloupe, West
Indies, 2019.
short: 'J. Ebbers, L. Drude, R. Haeb-Umbach, A. Brendel, W. Kellermann, in: CAMSAP
2019, Guadeloupe, West Indies, 2019.'
date_created: 2020-02-05T10:20:17Z
date_updated: 2023-11-22T08:29:58Z
ddc:
- '000'
department:
- _id: '54'
file:
- access_level: open_access
content_type: application/pdf
creator: huesera
date_created: 2020-02-05T10:21:39Z
date_updated: 2020-02-05T10:21:39Z
file_id: '15797'
file_name: CAMSAP_2019_WS_Ebbers_Paper.pdf
file_size: 311887
relation: main_file
file_date_updated: 2020-02-05T10:21:39Z
has_accepted_license: '1'
language:
- iso: eng
oa: '1'
project:
- _id: '52'
name: Computing Resources Provided by the Paderborn Center for Parallel Computing
publication: CAMSAP 2019, Guadeloupe, West Indies
quality_controlled: '1'
status: public
title: Weakly Supervised Sound Activity Detection and Event Classification in Acoustic
Sensor Networks
type: conference
user_id: '34851'
year: '2019'
...
---
_id: '15792'
abstract:
- lang: eng
text: In this paper we highlight the privacy risks entailed in deep neural network
feature extraction for domestic activity monitoring. We employ the baseline system
proposed in the Task 5 of the DCASE 2018 challenge and simulate a feature interception
attack by an eavesdropper who wants to perform speaker identification. We then
propose to reduce the aforementioned privacy risks by introducing a variational
information feature extraction scheme that allows for good activity monitoring
performance while at the same time minimizing the information of the feature representation,
thus restricting speaker identification attempts. We analyze the resulting model’s
composite loss function and the budget scaling factor used to control the balance
between the performance of the trusted and attacker tasks. It is empirically demonstrated
that the proposed method reduces speaker identification privacy risks without
significantly deprecating the performance of domestic activity monitoring tasks.
author:
- first_name: Alexandru
full_name: Nelus, Alexandru
last_name: Nelus
- 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: Rainer
full_name: Martin, Rainer
last_name: Martin
citation:
ama: 'Nelus A, Ebbers J, Haeb-Umbach R, Martin R. Privacy-preserving Variational
Information Feature Extraction for Domestic Activity Monitoring Versus Speaker
Identification. In: INTERSPEECH 2019, Graz, Austria. ; 2019.'
apa: Nelus, A., Ebbers, J., Haeb-Umbach, R., & Martin, R. (2019). Privacy-preserving
Variational Information Feature Extraction for Domestic Activity Monitoring Versus
Speaker Identification. INTERSPEECH 2019, Graz, Austria.
bibtex: '@inproceedings{Nelus_Ebbers_Haeb-Umbach_Martin_2019, title={Privacy-preserving
Variational Information Feature Extraction for Domestic Activity Monitoring Versus
Speaker Identification}, booktitle={INTERSPEECH 2019, Graz, Austria}, author={Nelus,
Alexandru and Ebbers, Janek and Haeb-Umbach, Reinhold and Martin, Rainer}, year={2019}
}'
chicago: Nelus, Alexandru, Janek Ebbers, Reinhold Haeb-Umbach, and Rainer Martin.
“Privacy-Preserving Variational Information Feature Extraction for Domestic Activity
Monitoring Versus Speaker Identification.” In INTERSPEECH 2019, Graz, Austria,
2019.
ieee: A. Nelus, J. Ebbers, R. Haeb-Umbach, and R. Martin, “Privacy-preserving Variational
Information Feature Extraction for Domestic Activity Monitoring Versus Speaker
Identification,” 2019.
mla: Nelus, Alexandru, et al. “Privacy-Preserving Variational Information Feature
Extraction for Domestic Activity Monitoring Versus Speaker Identification.” INTERSPEECH
2019, Graz, Austria, 2019.
short: 'A. Nelus, J. Ebbers, R. Haeb-Umbach, R. Martin, in: INTERSPEECH 2019, Graz,
Austria, 2019.'
date_created: 2020-02-05T10:07:53Z
date_updated: 2023-11-22T08:27:55Z
ddc:
- '000'
department:
- _id: '54'
file:
- access_level: open_access
content_type: application/pdf
creator: huesera
date_created: 2020-02-05T10:11:40Z
date_updated: 2020-02-05T10:11:40Z
file_id: '15793'
file_name: INTERSPEECH_2019_Ebbers_Paper.pdf
file_size: 454600
relation: main_file
file_date_updated: 2020-02-05T10:11:40Z
has_accepted_license: '1'
language:
- iso: eng
oa: '1'
publication: INTERSPEECH 2019, Graz, Austria
quality_controlled: '1'
status: public
title: Privacy-preserving Variational Information Feature Extraction for Domestic
Activity Monitoring Versus Speaker Identification
type: conference
user_id: '34851'
year: '2019'
...
---
_id: '11760'
abstract:
- lang: eng
text: Acoustic event detection, i.e., the task of assigning a human interpretable
label to a segment of audio, has only recently attracted increased interest in
the research community. Driven by the DCASE challenges and the availability of
large-scale audio datasets, the state-of-the-art has progressed rapidly with deep-learning-based
classi- fiers dominating the field. Because several potential use cases favor
a realization on distributed sensor nodes, e.g. ambient assisted living applications,
habitat monitoring or surveillance, we are concerned with two issues here. Firstly
the classification performance of such systems and secondly the computing resources
required to achieve a certain performance considering node level feature extraction.
In this contribution we look at the balance between the two criteria by employing
traditional techniques and different deep learning architectures, including convolutional
and recurrent models in the context of real life everyday audio recordings in
realistic, however challenging, multisource conditions.
author:
- first_name: Janek
full_name: Ebbers, Janek
id: '34851'
last_name: Ebbers
- first_name: Alexandru
full_name: Nelus, Alexandru
last_name: Nelus
- first_name: Rainer
full_name: Martin, Rainer
last_name: Martin
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Ebbers J, Nelus A, Martin R, Haeb-Umbach R. Evaluation of Modulation-MFCC
Features and DNN Classification for Acoustic Event Detection. In: DAGA 2018,
München. ; 2018.'
apa: Ebbers, J., Nelus, A., Martin, R., & Haeb-Umbach, R. (2018). Evaluation
of Modulation-MFCC Features and DNN Classification for Acoustic Event Detection.
In DAGA 2018, München.
bibtex: '@inproceedings{Ebbers_Nelus_Martin_Haeb-Umbach_2018, title={Evaluation
of Modulation-MFCC Features and DNN Classification for Acoustic Event Detection},
booktitle={DAGA 2018, München}, author={Ebbers, Janek and Nelus, Alexandru and
Martin, Rainer and Haeb-Umbach, Reinhold}, year={2018} }'
chicago: Ebbers, Janek, Alexandru Nelus, Rainer Martin, and Reinhold Haeb-Umbach.
“Evaluation of Modulation-MFCC Features and DNN Classification for Acoustic Event
Detection.” In DAGA 2018, München, 2018.
ieee: J. Ebbers, A. Nelus, R. Martin, and R. Haeb-Umbach, “Evaluation of Modulation-MFCC
Features and DNN Classification for Acoustic Event Detection,” in DAGA 2018,
München, 2018.
mla: Ebbers, Janek, et al. “Evaluation of Modulation-MFCC Features and DNN Classification
for Acoustic Event Detection.” DAGA 2018, München, 2018.
short: 'J. Ebbers, A. Nelus, R. Martin, R. Haeb-Umbach, in: DAGA 2018, München,
2018.'
date_created: 2019-07-12T05:27:43Z
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/2018/Daga_2018_Ebbers_Paper.pdf
oa: '1'
publication: DAGA 2018, München
status: public
title: Evaluation of Modulation-MFCC Features and DNN Classification for Acoustic
Event Detection
type: conference
user_id: '44006'
year: '2018'
...
---
_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: '11836'
abstract:
- lang: eng
text: Due to their distributed nature wireless acoustic sensor networks offer great
potential for improved signal acquisition, processing and classification for applications
such as monitoring and surveillance, home automation, or hands-free telecommunication.
To reduce the communication demand with a central server and to raise the privacy
level it is desirable to perform processing at node level. The limited processing
and memory capabilities on a sensor node, however, stand in contrast to the compute
and memory intensive deep learning algorithms used in modern speech and audio
processing. In this work, we perform benchmarking of commonly used convolutional
and recurrent neural network architectures on a Raspberry Pi based acoustic sensor
node. We show that it is possible to run medium-sized neural network topologies
used for speech enhancement and speech recognition in real time. For acoustic
event recognition, where predictions in a lower temporal resolution are sufficient,
it is even possible to run current state-of-the-art deep convolutional models
with a real-time-factor of 0:11.
author:
- first_name: Janek
full_name: Ebbers, Janek
id: '34851'
last_name: Ebbers
- first_name: Jens
full_name: Heitkaemper, Jens
id: '27643'
last_name: Heitkaemper
- first_name: Joerg
full_name: Schmalenstroeer, Joerg
id: '460'
last_name: Schmalenstroeer
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Ebbers J, Heitkaemper J, Schmalenstroeer J, Haeb-Umbach R. Benchmarking Neural
Network Architectures for Acoustic Sensor Networks. In: ITG 2018, Oldenburg,
Germany. ; 2018.'
apa: Ebbers, J., Heitkaemper, J., Schmalenstroeer, J., & Haeb-Umbach, R. (2018).
Benchmarking Neural Network Architectures for Acoustic Sensor Networks. ITG
2018, Oldenburg, Germany.
bibtex: '@inproceedings{Ebbers_Heitkaemper_Schmalenstroeer_Haeb-Umbach_2018, title={Benchmarking
Neural Network Architectures for Acoustic Sensor Networks}, booktitle={ITG 2018,
Oldenburg, Germany}, author={Ebbers, Janek and Heitkaemper, Jens and Schmalenstroeer,
Joerg and Haeb-Umbach, Reinhold}, year={2018} }'
chicago: Ebbers, Janek, Jens Heitkaemper, Joerg Schmalenstroeer, and Reinhold Haeb-Umbach.
“Benchmarking Neural Network Architectures for Acoustic Sensor Networks.” In ITG
2018, Oldenburg, Germany, 2018.
ieee: J. Ebbers, J. Heitkaemper, J. Schmalenstroeer, and R. Haeb-Umbach, “Benchmarking
Neural Network Architectures for Acoustic Sensor Networks,” 2018.
mla: Ebbers, Janek, et al. “Benchmarking Neural Network Architectures for Acoustic
Sensor Networks.” ITG 2018, Oldenburg, Germany, 2018.
short: 'J. Ebbers, J. Heitkaemper, J. Schmalenstroeer, R. Haeb-Umbach, in: ITG 2018,
Oldenburg, Germany, 2018.'
date_created: 2019-07-12T05:29:11Z
date_updated: 2023-10-26T08:12:40Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/2018/ITG_2018_Ebbers_Paper.pdf
oa: '1'
publication: ITG 2018, Oldenburg, Germany
quality_controlled: '1'
related_material:
link:
- description: Poster
relation: supplementary_material
url: https://groups.uni-paderborn.de/nt/pubs/2018/ITG_2018_Ebbers_Poster.pdf
status: public
title: Benchmarking Neural Network Architectures for Acoustic Sensor Networks
type: conference
user_id: '460'
year: '2018'
...
---
_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'
...