---
_id: '59999'
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: Fritz
full_name: Seebauer, Fritz
last_name: Seebauer
- first_name: Jana
full_name: Wiechmann, Jana
last_name: Wiechmann
- 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, Seebauer F, Wiechmann J, Wagner P, Haeb-Umbach R.
Speech Synthesis along Perceptual Voice Quality Dimensions. In: ICASSP 2025
- 2025 IEEE International Conference on Acoustics, Speech and Signal Processing
(ICASSP). IEEE; 2025. doi:10.1109/icassp49660.2025.10888012'
apa: Rautenberg, F., Kuhlmann, M., Seebauer, F., Wiechmann, J., Wagner, P., &
Haeb-Umbach, R. (2025). Speech Synthesis along Perceptual Voice Quality Dimensions.
ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal
Processing (ICASSP). IEEE International Conference on Acoustics, Speech and
Signal Processing (ICASSP), Hyderabad, India . https://doi.org/10.1109/icassp49660.2025.10888012
bibtex: '@inproceedings{Rautenberg_Kuhlmann_Seebauer_Wiechmann_Wagner_Haeb-Umbach_2025,
title={Speech Synthesis along Perceptual Voice Quality Dimensions}, DOI={10.1109/icassp49660.2025.10888012},
booktitle={ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech
and Signal Processing (ICASSP)}, publisher={IEEE}, author={Rautenberg, Frederik
and Kuhlmann, Michael and Seebauer, Fritz and Wiechmann, Jana and Wagner, Petra
and Haeb-Umbach, Reinhold}, year={2025} }'
chicago: Rautenberg, Frederik, Michael Kuhlmann, Fritz Seebauer, Jana Wiechmann,
Petra Wagner, and Reinhold Haeb-Umbach. “Speech Synthesis along Perceptual Voice
Quality Dimensions.” In ICASSP 2025 - 2025 IEEE International Conference on
Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2025. https://doi.org/10.1109/icassp49660.2025.10888012.
ieee: 'F. Rautenberg, M. Kuhlmann, F. Seebauer, J. Wiechmann, P. Wagner, and R.
Haeb-Umbach, “Speech Synthesis along Perceptual Voice Quality Dimensions,” presented
at the IEEE International Conference on Acoustics, Speech and Signal Processing
(ICASSP), Hyderabad, India , 2025, doi: 10.1109/icassp49660.2025.10888012.'
mla: Rautenberg, Frederik, et al. “Speech Synthesis along Perceptual Voice Quality
Dimensions.” ICASSP 2025 - 2025 IEEE International Conference on Acoustics,
Speech and Signal Processing (ICASSP), IEEE, 2025, doi:10.1109/icassp49660.2025.10888012.
short: 'F. Rautenberg, M. Kuhlmann, F. Seebauer, J. Wiechmann, P. Wagner, R. Haeb-Umbach,
in: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and
Signal Processing (ICASSP), IEEE, 2025.'
conference:
end_date: 2025-04-11
location: 'Hyderabad, India '
name: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
start_date: 2025-04-06
date_created: 2025-05-20T08:17:22Z
date_updated: 2025-05-26T11:09:56Z
department:
- _id: '54'
- _id: '660'
doi: 10.1109/icassp49660.2025.10888012
language:
- iso: eng
project:
- _id: '129'
grant_number: '438445824'
name: 'TRR 318 - C06: TRR 318 - Technisch unterstütztes Erklären von Stimmcharakteristika
(Teilprojekt C06)'
publication: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech
and Signal Processing (ICASSP)
publication_status: published
publisher: IEEE
status: public
title: Speech Synthesis along Perceptual Voice Quality Dimensions
type: conference
user_id: '72602'
year: '2025'
...
---
_id: '61047'
author:
- first_name: Frederik
full_name: Rautenberg, Frederik
id: '72602'
last_name: Rautenberg
- first_name: Fritz
full_name: Seebauer, Fritz
last_name: Seebauer
- first_name: Jana
full_name: Wiechmann, Jana
last_name: Wiechmann
- first_name: Michael
full_name: Kuhlmann, Michael
id: '49871'
last_name: Kuhlmann
- 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, Seebauer F, Wiechmann J, Kuhlmann M, Wagner P, Haeb-Umbach R.
Synthesizing Speech with Selected Perceptual Voice Qualities – A Case Study with
Creaky Voice. In: Interspeech 2025. ISCA; 2025. doi:10.21437/Interspeech.2025-1443'
apa: Rautenberg, F., Seebauer, F., Wiechmann, J., Kuhlmann, M., Wagner, P., &
Haeb-Umbach, R. (2025). Synthesizing Speech with Selected Perceptual Voice Qualities
– A Case Study with Creaky Voice. Interspeech 2025. Interspeech, Rotterdam.
https://doi.org/10.21437/Interspeech.2025-1443
bibtex: '@inproceedings{Rautenberg_Seebauer_Wiechmann_Kuhlmann_Wagner_Haeb-Umbach_2025,
title={Synthesizing Speech with Selected Perceptual Voice Qualities – A Case Study
with Creaky Voice}, DOI={10.21437/Interspeech.2025-1443},
booktitle={Interspeech 2025}, publisher={ISCA}, author={Rautenberg, Frederik and
Seebauer, Fritz and Wiechmann, Jana and Kuhlmann, Michael and Wagner, Petra and
Haeb-Umbach, Reinhold}, year={2025} }'
chicago: Rautenberg, Frederik, Fritz Seebauer, Jana Wiechmann, Michael Kuhlmann,
Petra Wagner, and Reinhold Haeb-Umbach. “Synthesizing Speech with Selected Perceptual
Voice Qualities – A Case Study with Creaky Voice.” In Interspeech 2025.
ISCA, 2025. https://doi.org/10.21437/Interspeech.2025-1443.
ieee: 'F. Rautenberg, F. Seebauer, J. Wiechmann, M. Kuhlmann, P. Wagner, and R.
Haeb-Umbach, “Synthesizing Speech with Selected Perceptual Voice Qualities – A
Case Study with Creaky Voice,” presented at the Interspeech, Rotterdam, 2025,
doi: 10.21437/Interspeech.2025-1443.'
mla: Rautenberg, Frederik, et al. “Synthesizing Speech with Selected Perceptual
Voice Qualities – A Case Study with Creaky Voice.” Interspeech 2025, ISCA,
2025, doi:10.21437/Interspeech.2025-1443.
short: 'F. Rautenberg, F. Seebauer, J. Wiechmann, M. Kuhlmann, P. Wagner, R. Haeb-Umbach,
in: Interspeech 2025, ISCA, 2025.'
conference:
end_date: 2025-08-21
location: Rotterdam
name: Interspeech
start_date: 2025-08-17
date_created: 2025-08-28T08:39:01Z
date_updated: 2025-08-28T08:56:49Z
department:
- _id: '54'
- _id: '660'
doi: 10.21437/Interspeech.2025-1443
language:
- iso: eng
project:
- _id: '129'
name: 'TRR 318; TP C06: Technisch unterstütztes Erklären von Stimmcharakteristika'
publication: Interspeech 2025
publisher: ISCA
status: public
title: Synthesizing Speech with Selected Perceptual Voice Qualities – A Case Study
with Creaky Voice
type: conference
user_id: '72602'
year: '2025'
...
---
_id: '61079'
abstract:
- lang: eng
text: "We propose a spatio-spectral, combined model-based and data-driven\r\ndiarization
pipeline consisting of TDOA-based segmentation followed by\r\nembedding-based
clustering. The proposed system requires neither access to\r\nmulti-channel training
data nor prior knowledge about the number or placement\r\nof microphones. It works
for both a compact microphone array and distributed\r\nmicrophones, with minor
adjustments. Due to its superior handling of\r\noverlapping speech during segmentation,
the proposed pipeline significantly\r\noutperforms the single-channel pyannote
approach, both in a scenario with a\r\ncompact microphone array and in a setup
with distributed microphones.\r\nAdditionally, we show that, unlike fully spatial
diarization pipelines, the\r\nproposed system can correctly track speakers when
they change positions."
author:
- first_name: Tobias
full_name: Cord-Landwehr, Tobias
id: '44393'
last_name: Cord-Landwehr
- first_name: Tobias
full_name: Gburrek, Tobias
id: '44006'
last_name: Gburrek
- first_name: Marc
full_name: Deegen, Marc
id: '70272'
last_name: Deegen
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Cord-Landwehr T, Gburrek T, Deegen M, Haeb-Umbach R. Spatio-spectral diarization
of meetings by combining TDOA-based segmentation and speaker embedding-based
clustering. In: Proceedings of INTERSPEECH. ; 2025. doi:10.21437/Interspeech.2025-1663'
apa: Cord-Landwehr, T., Gburrek, T., Deegen, M., & Haeb-Umbach, R. (2025). Spatio-spectral
diarization of meetings by combining TDOA-based segmentation and speaker embedding-based
clustering. Proceedings of INTERSPEECH. Interspeech 2025, Rotterdam. https://doi.org/10.21437/Interspeech.2025-1663
bibtex: '@inproceedings{Cord-Landwehr_Gburrek_Deegen_Haeb-Umbach_2025, title={Spatio-spectral
diarization of meetings by combining TDOA-based segmentation and speaker embedding-based
clustering}, DOI={10.21437/Interspeech.2025-1663},
booktitle={Proceedings of INTERSPEECH}, author={Cord-Landwehr, Tobias and Gburrek,
Tobias and Deegen, Marc and Haeb-Umbach, Reinhold}, year={2025} }'
chicago: Cord-Landwehr, Tobias, Tobias Gburrek, Marc Deegen, and Reinhold Haeb-Umbach.
“Spatio-Spectral Diarization of Meetings by Combining TDOA-Based Segmentation
and Speaker Embedding-Based Clustering.” In Proceedings of INTERSPEECH,
2025. https://doi.org/10.21437/Interspeech.2025-1663.
ieee: 'T. Cord-Landwehr, T. Gburrek, M. Deegen, and R. Haeb-Umbach, “Spatio-spectral
diarization of meetings by combining TDOA-based segmentation and speaker embedding-based
clustering,” presented at the Interspeech 2025, Rotterdam, 2025, doi: 10.21437/Interspeech.2025-1663.'
mla: Cord-Landwehr, Tobias, et al. “Spatio-Spectral Diarization of Meetings by Combining
TDOA-Based Segmentation and Speaker Embedding-Based Clustering.” Proceedings
of INTERSPEECH, 2025, doi:10.21437/Interspeech.2025-1663.
short: 'T. Cord-Landwehr, T. Gburrek, M. Deegen, R. Haeb-Umbach, in: Proceedings
of INTERSPEECH, 2025.'
conference:
location: Rotterdam
name: Interspeech 2025
date_created: 2025-08-29T09:39:01Z
date_updated: 2025-11-10T09:06:47Z
ddc:
- '000'
department:
- _id: '54'
doi: 10.21437/Interspeech.2025-1663
external_id:
arxiv:
- '2506.16228'
file:
- access_level: open_access
content_type: application/pdf
creator: cord
date_created: 2025-08-29T09:43:32Z
date_updated: 2025-08-29T09:43:32Z
file_id: '61085'
file_name: main.pdf
file_size: 921918
relation: main_file
file_date_updated: 2025-08-29T09:43:32Z
has_accepted_license: '1'
language:
- iso: eng
oa: '1'
project:
- _id: '52'
name: Computing Resources Provided by the Paderborn Center for Parallel Computing
publication: Proceedings of INTERSPEECH
status: public
title: Spatio-spectral diarization of meetings by combining TDOA-based segmentation
and speaker embedding-based clustering
type: conference
user_id: '44393'
year: '2025'
...
---
_id: '62164'
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: Petra
full_name: Wagner, Petra
id: '74505'
last_name: Wagner
- first_name: Reinhold
full_name: Häb-Umbach, Reinhold
id: '242'
last_name: Häb-Umbach
citation:
ama: 'Kuhlmann M, Seebauer F, Wagner P, Häb-Umbach R. Towards Frame-level Quality
Predictions of Synthetic Speech. In: Interspeech 2025. ISCA; 2025. doi:10.21437/interspeech.2025-2190'
apa: Kuhlmann, M., Seebauer, F., Wagner, P., & Häb-Umbach, R. (2025). Towards
Frame-level Quality Predictions of Synthetic Speech. Interspeech 2025.
https://doi.org/10.21437/interspeech.2025-2190
bibtex: '@inproceedings{Kuhlmann_Seebauer_Wagner_Häb-Umbach_2025, title={Towards
Frame-level Quality Predictions of Synthetic Speech}, DOI={10.21437/interspeech.2025-2190},
booktitle={Interspeech 2025}, publisher={ISCA}, author={Kuhlmann, Michael and
Seebauer, Fritz and Wagner, Petra and Häb-Umbach, Reinhold}, year={2025} }'
chicago: Kuhlmann, Michael, Fritz Seebauer, Petra Wagner, and Reinhold Häb-Umbach.
“Towards Frame-Level Quality Predictions of Synthetic Speech.” In Interspeech
2025. ISCA, 2025. https://doi.org/10.21437/interspeech.2025-2190.
ieee: 'M. Kuhlmann, F. Seebauer, P. Wagner, and R. Häb-Umbach, “Towards Frame-level
Quality Predictions of Synthetic Speech,” 2025, doi: 10.21437/interspeech.2025-2190.'
mla: Kuhlmann, Michael, et al. “Towards Frame-Level Quality Predictions of Synthetic
Speech.” Interspeech 2025, ISCA, 2025, doi:10.21437/interspeech.2025-2190.
short: 'M. Kuhlmann, F. Seebauer, P. Wagner, R. Häb-Umbach, in: Interspeech 2025,
ISCA, 2025.'
date_created: 2025-11-11T11:43:20Z
date_updated: 2025-11-11T11:45:12Z
department:
- _id: '54'
doi: 10.21437/interspeech.2025-2190
language:
- iso: eng
publication: Interspeech 2025
publication_status: published
publisher: ISCA
status: public
title: Towards Frame-level Quality Predictions of Synthetic Speech
type: conference
user_id: '49871'
year: '2025'
...
---
_id: '62163'
abstract:
- lang: eng
text: Zero-shot classifiers based on Contrastive Language-Audio Pretraining (CLAP)
models enable classification of given audio into classes defined at test time
using text. These models are costly to run with respect to computation and memory
requirements. In this work, we propose to build a specialized low-resource classifier
for classes pre-defined using text, using a two-stage procedure consisting of
zero-shot data set pruning and model compression. First, relevant in-domain data
is selected from a source dataset using class label embeddings obtained from a
pre-trained CLAP model. This data is then used to distill the audio encoder of
a CLAP model. The proposed compression method produces compact audio encoders
with slightly reduced accuracy. Note that neither labeled nor unlabeled in-domain
audio data is required for its development. We verify by cross-dataset tests that
the resulting classifiers are indeed specialized to their task.
author:
- first_name: Alexander
full_name: Werning, Alexander
id: '62152'
last_name: Werning
- first_name: Reinhold
full_name: Häb-Umbach, Reinhold
id: '242'
last_name: Häb-Umbach
citation:
ama: 'Werning A, Häb-Umbach R. A Fully Zero-Shot Approach to Obtaining Specialized
and Compact Audio Tagging Models. In: Möller S, Gerkmann T, Kolossa D, eds. Proceedings
of the 16th ITG Conference on Speech Communication. ; 2025:76-80.'
apa: Werning, A., & Häb-Umbach, R. (2025). A Fully Zero-Shot Approach to Obtaining
Specialized and Compact Audio Tagging Models. In S. Möller, T. Gerkmann, &
D. Kolossa (Eds.), Proceedings of the 16th ITG Conference on Speech Communication
(pp. 76–80).
bibtex: '@inproceedings{Werning_Häb-Umbach_2025, place={Berlin}, title={A Fully
Zero-Shot Approach to Obtaining Specialized and Compact Audio Tagging Models},
booktitle={Proceedings of the 16th ITG Conference on Speech Communication}, author={Werning,
Alexander and Häb-Umbach, Reinhold}, editor={Möller, Sebastian and Gerkmann, Timo
and Kolossa, Dorothea}, year={2025}, pages={76–80} }'
chicago: Werning, Alexander, and Reinhold Häb-Umbach. “A Fully Zero-Shot Approach
to Obtaining Specialized and Compact Audio Tagging Models.” In Proceedings
of the 16th ITG Conference on Speech Communication, edited by Sebastian Möller,
Timo Gerkmann, and Dorothea Kolossa, 76–80. Berlin, 2025.
ieee: A. Werning and R. Häb-Umbach, “A Fully Zero-Shot Approach to Obtaining Specialized
and Compact Audio Tagging Models,” in Proceedings of the 16th ITG Conference
on Speech Communication, Berlin, 2025, pp. 76–80.
mla: Werning, Alexander, and Reinhold Häb-Umbach. “A Fully Zero-Shot Approach to
Obtaining Specialized and Compact Audio Tagging Models.” Proceedings of the
16th ITG Conference on Speech Communication, edited by Sebastian Möller et
al., 2025, pp. 76–80.
short: 'A. Werning, R. Häb-Umbach, in: S. Möller, T. Gerkmann, D. Kolossa (Eds.),
Proceedings of the 16th ITG Conference on Speech Communication, Berlin, 2025,
pp. 76–80.'
conference:
end_date: 2025-09-26
location: Berlin
name: 16th ITG Conference on Speech Communication
start_date: 2025-09-24
date_created: 2025-11-11T11:46:42Z
date_updated: 2025-11-28T13:20:17Z
department:
- _id: '54'
editor:
- first_name: Sebastian
full_name: Möller, Sebastian
last_name: Möller
- first_name: Timo
full_name: Gerkmann, Timo
last_name: Gerkmann
- first_name: Dorothea
full_name: Kolossa, Dorothea
last_name: Kolossa
language:
- iso: eng
page: 76-80
place: Berlin
project:
- _id: '512'
name: WestAI - AI Service Center West
publication: Proceedings of the 16th ITG Conference on Speech Communication
publication_identifier:
unknown:
- 978-3-8007-6617-8
publication_status: published
quality_controlled: '1'
status: public
title: A Fully Zero-Shot Approach to Obtaining Specialized and Compact Audio Tagging
Models
type: conference
user_id: '62152'
year: '2025'
...
---
_id: '59900'
abstract:
- lang: eng
text: Running state-of-the-art large-scale audio models on edge devices is often
infeasible due to their limited storage and computing resources. It is therefore
necessary to compress and tune the models for the specific target task and hardware.
This is commonly achieved by distilling the audio model, the teacher, to a small
target model, the student. However, this approach can be improved by prepending
a dataset pruning stage and training the teacher on the pruned data set only,
which contains examples relevant to the target task. Recently, CLAP models have
emerged that embed audio and text examples in a common embedding space. We use
the audio embeddings of the CLAP model for the above pruning stage, which is realized
using a domain classifier. After knowledge distillation, the student is eventually
fine-tuned on some data from the target domain. The CLAP architecture combines
text and audio embedding spaces, which allows to search for data given only a
textual description, such as a class label. We show how this can help data pruning.
author:
- first_name: Alexander
full_name: Werning, Alexander
id: '62152'
last_name: Werning
- first_name: Reinhold
full_name: Häb-Umbach, Reinhold
id: '242'
last_name: Häb-Umbach
citation:
ama: 'Werning A, Häb-Umbach R. Distilling Efficient Audio Models using Data Pruning
with CLAP. In: Deutsche Gesellschaft für Akustik e.V. (DEGA), Berlin, 2025, ed.
Proceedings of DAS|DAGA 2025. ; 2025.'
apa: Werning, A., & Häb-Umbach, R. (2025). Distilling Efficient Audio Models
using Data Pruning with CLAP. In Deutsche Gesellschaft für Akustik e.V. (DEGA),
Berlin, 2025 (Ed.), Proceedings of DAS|DAGA 2025.
bibtex: '@inproceedings{Werning_Häb-Umbach_2025, place={Copenhagen}, title={Distilling
Efficient Audio Models using Data Pruning with CLAP}, booktitle={Proceedings of
DAS|DAGA 2025}, author={Werning, Alexander and Häb-Umbach, Reinhold}, editor={Deutsche
Gesellschaft für Akustik e.V. (DEGA), Berlin, 2025}, year={2025} }'
chicago: Werning, Alexander, and Reinhold Häb-Umbach. “Distilling Efficient Audio
Models Using Data Pruning with CLAP.” In Proceedings of DAS|DAGA 2025,
edited by Deutsche Gesellschaft für Akustik e.V. (DEGA), Berlin, 2025. Copenhagen,
2025.
ieee: A. Werning and R. Häb-Umbach, “Distilling Efficient Audio Models using Data
Pruning with CLAP,” in Proceedings of DAS|DAGA 2025, Copenhagen, 2025.
mla: Werning, Alexander, and Reinhold Häb-Umbach. “Distilling Efficient Audio Models
Using Data Pruning with CLAP.” Proceedings of DAS|DAGA 2025, edited by
Deutsche Gesellschaft für Akustik e.V. (DEGA), Berlin, 2025, 2025.
short: 'A. Werning, R. Häb-Umbach, in: Deutsche Gesellschaft für Akustik e.V. (DEGA),
Berlin, 2025 (Ed.), Proceedings of DAS|DAGA 2025, Copenhagen, 2025.'
conference:
end_date: 2025-03-20
location: Copenhagen
name: DAS|DAGA 2025 - 51st Annual Meeting on Acoustics
start_date: 2025-03-17
corporate_editor:
- Deutsche Gesellschaft für Akustik e.V. (DEGA), Berlin, 2025
date_created: 2025-05-14T13:18:10Z
date_updated: 2025-11-28T13:21:13Z
ddc:
- '004'
department:
- _id: '54'
has_accepted_license: '1'
language:
- iso: eng
place: Copenhagen
project:
- _id: '512'
name: WestAI - AI Service Center West
publication: Proceedings of DAS|DAGA 2025
publication_identifier:
unknown:
- 978-3-939296-23-2
publication_status: published
status: public
title: Distilling Efficient Audio Models using Data Pruning with CLAP
type: conference
user_id: '62152'
year: '2025'
...
---
_id: '62174'
author:
- first_name: Adrian Tobias
full_name: Meise, Adrian Tobias
id: '79268'
last_name: Meise
- 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: 'Meise AT, Cord-Landwehr T, Haeb-Umbach R. On the Application of Diffusion
Models for Simultaneous Denoising and Dereverberation. In: ITG Conference
on Speech Communication. ; 2025.'
apa: Meise, A. T., Cord-Landwehr, T., & Haeb-Umbach, R. (2025). On the Application
of Diffusion Models for Simultaneous Denoising and Dereverberation. ITG Conference
on Speech Communication. ITG Conference on Speech Communication, Berlin.
bibtex: '@inproceedings{Meise_Cord-Landwehr_Haeb-Umbach_2025, title={On the Application
of Diffusion Models for Simultaneous Denoising and Dereverberation}, booktitle={
ITG Conference on Speech Communication}, author={Meise, Adrian Tobias and Cord-Landwehr,
Tobias and Haeb-Umbach, Reinhold}, year={2025} }'
chicago: Meise, Adrian Tobias, Tobias Cord-Landwehr, and Reinhold Haeb-Umbach. “On
the Application of Diffusion Models for Simultaneous Denoising and Dereverberation.”
In ITG Conference on Speech Communication, 2025.
ieee: A. T. Meise, T. Cord-Landwehr, and R. Haeb-Umbach, “On the Application of
Diffusion Models for Simultaneous Denoising and Dereverberation,” presented at
the ITG Conference on Speech Communication, Berlin, 2025.
mla: Meise, Adrian Tobias, et al. “On the Application of Diffusion Models for Simultaneous
Denoising and Dereverberation.” ITG Conference on Speech Communication,
2025.
short: 'A.T. Meise, T. Cord-Landwehr, R. Haeb-Umbach, in: ITG Conference on Speech
Communication, 2025.'
conference:
location: Berlin
name: ITG Conference on Speech Communication
date_created: 2025-11-13T07:21:51Z
date_updated: 2026-01-05T09:05:14Z
department:
- _id: '54'
language:
- iso: eng
publication: ' ITG Conference on Speech Communication'
publication_identifier:
isbn:
- 978-3-8007-6617-8
status: public
title: On the Application of Diffusion Models for Simultaneous Denoising and Dereverberation
type: conference
user_id: '44393'
year: '2025'
...
---
_id: '52958'
author:
- first_name: Christoph
full_name: Boeddeker, Christoph
id: '40767'
last_name: Boeddeker
- first_name: Aswin Shanmugam
full_name: Subramanian, Aswin Shanmugam
last_name: Subramanian
- first_name: Gordon
full_name: Wichern, Gordon
last_name: Wichern
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
- first_name: Jonathan
full_name: Le Roux, Jonathan
last_name: Le Roux
citation:
ama: 'Boeddeker C, Subramanian AS, Wichern G, Haeb-Umbach R, Le Roux J. TS-SEP:
Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings.
IEEE/ACM Transactions on Audio, Speech, and Language Processing. 2024;32:1185-1197.
doi:10.1109/taslp.2024.3350887'
apa: 'Boeddeker, C., Subramanian, A. S., Wichern, G., Haeb-Umbach, R., & Le
Roux, J. (2024). TS-SEP: Joint Diarization and Separation Conditioned on Estimated
Speaker Embeddings. IEEE/ACM Transactions on Audio, Speech, and Language Processing,
32, 1185–1197. https://doi.org/10.1109/taslp.2024.3350887'
bibtex: '@article{Boeddeker_Subramanian_Wichern_Haeb-Umbach_Le Roux_2024, title={TS-SEP:
Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings},
volume={32}, DOI={10.1109/taslp.2024.3350887},
journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing}, publisher={Institute
of Electrical and Electronics Engineers (IEEE)}, author={Boeddeker, Christoph
and Subramanian, Aswin Shanmugam and Wichern, Gordon and Haeb-Umbach, Reinhold
and Le Roux, Jonathan}, year={2024}, pages={1185–1197} }'
chicago: 'Boeddeker, Christoph, Aswin Shanmugam Subramanian, Gordon Wichern, Reinhold
Haeb-Umbach, and Jonathan Le Roux. “TS-SEP: Joint Diarization and Separation Conditioned
on Estimated Speaker Embeddings.” IEEE/ACM Transactions on Audio, Speech, and
Language Processing 32 (2024): 1185–97. https://doi.org/10.1109/taslp.2024.3350887.'
ieee: 'C. Boeddeker, A. S. Subramanian, G. Wichern, R. Haeb-Umbach, and J. Le Roux,
“TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings,”
IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 32,
pp. 1185–1197, 2024, doi: 10.1109/taslp.2024.3350887.'
mla: 'Boeddeker, Christoph, et al. “TS-SEP: Joint Diarization and Separation Conditioned
on Estimated Speaker Embeddings.” IEEE/ACM Transactions on Audio, Speech, and
Language Processing, vol. 32, Institute of Electrical and Electronics Engineers
(IEEE), 2024, pp. 1185–97, doi:10.1109/taslp.2024.3350887.'
short: C. Boeddeker, A.S. Subramanian, G. Wichern, R. Haeb-Umbach, J. Le Roux, IEEE/ACM
Transactions on Audio, Speech, and Language Processing 32 (2024) 1185–1197.
date_created: 2024-03-26T16:11:54Z
date_updated: 2025-04-16T10:21:45Z
ddc:
- '000'
department:
- _id: '54'
doi: 10.1109/taslp.2024.3350887
file:
- access_level: open_access
content_type: application/pdf
creator: cbj
date_created: 2025-04-16T10:14:47Z
date_updated: 2025-04-16T10:21:45Z
file_id: '59602'
file_name: main.pdf
file_size: 3432879
relation: main_file
- access_level: open_access
content_type: application/pdf
creator: cbj
date_created: 2025-04-16T10:15:08Z
date_updated: 2025-04-16T10:21:45Z
file_id: '59603'
file_name: slides.pdf
file_size: 2838635
relation: main_file
- access_level: open_access
content_type: application/pdf
creator: cbj
date_created: 2025-04-16T10:15:22Z
date_updated: 2025-04-16T10:21:45Z
file_id: '59604'
file_name: poster.pdf
file_size: 2038741
relation: main_file
file_date_updated: 2025-04-16T10:21:45Z
has_accepted_license: '1'
intvolume: ' 32'
keyword:
- Electrical and Electronic Engineering
- Acoustics and Ultrasonics
- Computer Science (miscellaneous)
- Computational Mathematics
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://arxiv.org/abs/2303.03849
oa: '1'
page: 1185-1197
project:
- _id: '52'
name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing'
- _id: '508'
grant_number: '448568305'
name: Automatische Transkription von Gesprächssituationen
publication: IEEE/ACM Transactions on Audio, Speech, and Language Processing
publication_identifier:
issn:
- 2329-9290
- 2329-9304
publication_status: published
publisher: Institute of Electrical and Electronics Engineers (IEEE)
status: public
title: 'TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker
Embeddings'
type: journal_article
user_id: '40767'
volume: 32
year: '2024'
...
---
_id: '57161'
author:
- first_name: Alexander
full_name: Werning, Alexander
id: '62152'
last_name: Werning
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Werning A, Haeb-Umbach R. UPB-NT Submission to DCASE24: Dataset Pruning
for Targeted Knowledge Distillation.; 2024.'
apa: 'Werning, A., & Haeb-Umbach, R. (2024). UPB-NT submission to DCASE24:
Dataset pruning for targeted knowledge distillation.'
bibtex: '@book{Werning_Haeb-Umbach_2024, title={UPB-NT submission to DCASE24: Dataset
pruning for targeted knowledge distillation}, author={Werning, Alexander and Haeb-Umbach,
Reinhold}, year={2024} }'
chicago: 'Werning, Alexander, and Reinhold Haeb-Umbach. UPB-NT Submission to
DCASE24: Dataset Pruning for Targeted Knowledge Distillation, 2024.'
ieee: 'A. Werning and R. Haeb-Umbach, UPB-NT submission to DCASE24: Dataset pruning
for targeted knowledge distillation. 2024.'
mla: 'Werning, Alexander, and Reinhold Haeb-Umbach. UPB-NT Submission to DCASE24:
Dataset Pruning for Targeted Knowledge Distillation. 2024.'
short: 'A. Werning, R. Haeb-Umbach, UPB-NT Submission to DCASE24: Dataset Pruning
for Targeted Knowledge Distillation, 2024.'
date_created: 2024-11-18T09:44:46Z
date_updated: 2024-11-18T09:45:14Z
department:
- _id: '54'
language:
- iso: eng
project:
- _id: '512'
name: WestAI - AI Service Center West
status: public
title: 'UPB-NT submission to DCASE24: Dataset pruning for targeted knowledge distillation'
type: report
user_id: '62152'
year: '2024'
...
---
_id: '57099'
author:
- first_name: Yuying
full_name: Xie, Yuying
last_name: Xie
- first_name: Michael
full_name: Kuhlmann, Michael
id: '49871'
last_name: Kuhlmann
- first_name: Frederik
full_name: Rautenberg, Frederik
id: '72602'
last_name: Rautenberg
- first_name: Zheng-Hua
full_name: Tan, Zheng-Hua
last_name: Tan
- first_name: Reinhold
full_name: Häb-Umbach, Reinhold
id: '242'
last_name: Häb-Umbach
citation:
ama: 'Xie Y, Kuhlmann M, Rautenberg F, Tan Z-H, Häb-Umbach R. Speaker and Style
Disentanglement of Speech Based on Contrastive Predictive Coding Supported Factorized
Variational Autoencoder. In: 2024 32nd European Signal Processing Conference
(EUSIPCO). ; 2024:436–440.'
apa: Xie, Y., Kuhlmann, M., Rautenberg, F., Tan, Z.-H., & Häb-Umbach, R. (2024).
Speaker and Style Disentanglement of Speech Based on Contrastive Predictive Coding
Supported Factorized Variational Autoencoder. 2024 32nd European Signal Processing
Conference (EUSIPCO), 436–440.
bibtex: '@inproceedings{Xie_Kuhlmann_Rautenberg_Tan_Häb-Umbach_2024, title={Speaker
and Style Disentanglement of Speech Based on Contrastive Predictive Coding Supported
Factorized Variational Autoencoder}, booktitle={2024 32nd European Signal Processing
Conference (EUSIPCO)}, author={Xie, Yuying and Kuhlmann, Michael and Rautenberg,
Frederik and Tan, Zheng-Hua and Häb-Umbach, Reinhold}, year={2024}, pages={436–440}
}'
chicago: Xie, Yuying, Michael Kuhlmann, Frederik Rautenberg, Zheng-Hua Tan, and
Reinhold Häb-Umbach. “Speaker and Style Disentanglement of Speech Based on Contrastive
Predictive Coding Supported Factorized Variational Autoencoder.” In 2024 32nd
European Signal Processing Conference (EUSIPCO), 436–440, 2024.
ieee: Y. Xie, M. Kuhlmann, F. Rautenberg, Z.-H. Tan, and R. Häb-Umbach, “Speaker
and Style Disentanglement of Speech Based on Contrastive Predictive Coding Supported
Factorized Variational Autoencoder,” in 2024 32nd European Signal Processing
Conference (EUSIPCO), 2024, pp. 436–440.
mla: Xie, Yuying, et al. “Speaker and Style Disentanglement of Speech Based on Contrastive
Predictive Coding Supported Factorized Variational Autoencoder.” 2024 32nd
European Signal Processing Conference (EUSIPCO), 2024, pp. 436–440.
short: 'Y. Xie, M. Kuhlmann, F. Rautenberg, Z.-H. Tan, R. Häb-Umbach, in: 2024 32nd
European Signal Processing Conference (EUSIPCO), 2024, pp. 436–440.'
date_created: 2024-11-15T06:52:54Z
date_updated: 2024-11-15T06:54:40Z
department:
- _id: '54'
language:
- iso: eng
page: 436–440
publication: 2024 32nd European Signal Processing Conference (EUSIPCO)
status: public
title: Speaker and Style Disentanglement of Speech Based on Contrastive Predictive
Coding Supported Factorized Variational Autoencoder
type: conference
user_id: '49871'
year: '2024'
...
---
_id: '56004'
author:
- first_name: Thilo
full_name: von Neumann, Thilo
id: '49870'
last_name: von Neumann
orcid: https://orcid.org/0000-0002-7717-8670
- first_name: Christoph
full_name: Boeddeker, Christoph
id: '40767'
last_name: Boeddeker
- first_name: Tobias
full_name: Cord-Landwehr, Tobias
id: '44393'
last_name: Cord-Landwehr
- first_name: Marc
full_name: Delcroix, Marc
last_name: Delcroix
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'von Neumann T, Boeddeker C, Cord-Landwehr T, Delcroix M, Haeb-Umbach R. Meeting
Recognition with Continuous Speech Separation and Transcription-Supported Diarization.
In: 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing
Workshops (ICASSPW). IEEE; 2024. doi:10.1109/icasspw62465.2024.10625894'
apa: von Neumann, T., Boeddeker, C., Cord-Landwehr, T., Delcroix, M., & Haeb-Umbach,
R. (2024). Meeting Recognition with Continuous Speech Separation and Transcription-Supported
Diarization. 2024 IEEE International Conference on Acoustics, Speech, and Signal
Processing Workshops (ICASSPW). https://doi.org/10.1109/icasspw62465.2024.10625894
bibtex: '@inproceedings{von Neumann_Boeddeker_Cord-Landwehr_Delcroix_Haeb-Umbach_2024,
title={Meeting Recognition with Continuous Speech Separation and Transcription-Supported
Diarization}, DOI={10.1109/icasspw62465.2024.10625894},
booktitle={2024 IEEE International Conference on Acoustics, Speech, and Signal
Processing Workshops (ICASSPW)}, publisher={IEEE}, author={von Neumann, Thilo
and Boeddeker, Christoph and Cord-Landwehr, Tobias and Delcroix, Marc and Haeb-Umbach,
Reinhold}, year={2024} }'
chicago: Neumann, Thilo von, Christoph Boeddeker, Tobias Cord-Landwehr, Marc Delcroix,
and Reinhold Haeb-Umbach. “Meeting Recognition with Continuous Speech Separation
and Transcription-Supported Diarization.” In 2024 IEEE International Conference
on Acoustics, Speech, and Signal Processing Workshops (ICASSPW). IEEE, 2024.
https://doi.org/10.1109/icasspw62465.2024.10625894.
ieee: 'T. von Neumann, C. Boeddeker, T. Cord-Landwehr, M. Delcroix, and R. Haeb-Umbach,
“Meeting Recognition with Continuous Speech Separation and Transcription-Supported
Diarization,” 2024, doi: 10.1109/icasspw62465.2024.10625894.'
mla: von Neumann, Thilo, et al. “Meeting Recognition with Continuous Speech Separation
and Transcription-Supported Diarization.” 2024 IEEE International Conference
on Acoustics, Speech, and Signal Processing Workshops (ICASSPW), IEEE, 2024,
doi:10.1109/icasspw62465.2024.10625894.
short: 'T. von Neumann, C. Boeddeker, T. Cord-Landwehr, M. Delcroix, R. Haeb-Umbach,
in: 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing
Workshops (ICASSPW), IEEE, 2024.'
date_created: 2024-09-04T07:26:02Z
date_updated: 2025-02-12T09:20:07Z
ddc:
- '000'
department:
- _id: '54'
doi: 10.1109/icasspw62465.2024.10625894
file:
- access_level: open_access
content_type: application/pdf
creator: tvn
date_created: 2024-09-04T07:34:30Z
date_updated: 2024-09-04T07:34:30Z
file_id: '56005'
file_name: main.pdf
file_size: 150432
relation: main_file
file_date_updated: 2024-09-04T07:34:30Z
has_accepted_license: '1'
language:
- iso: eng
oa: '1'
project:
- _id: '52'
name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing'
- _id: '508'
grant_number: '448568305'
name: Automatische Transkription von Gesprächssituationen
publication: 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing
Workshops (ICASSPW)
publication_status: published
publisher: IEEE
status: public
title: Meeting Recognition with Continuous Speech Separation and Transcription-Supported
Diarization
type: conference
user_id: '40767'
year: '2024'
...
---
_id: '56272'
author:
- first_name: Christoph
full_name: Boeddeker, Christoph
id: '40767'
last_name: Boeddeker
- 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: 'Boeddeker C, Cord-Landwehr T, Haeb-Umbach R. Once more Diarization: Improving
meeting transcription systems through segment-level speaker reassignment. In:
Interspeech 2024. ISCA; 2024. doi:10.21437/interspeech.2024-1286'
apa: 'Boeddeker, C., Cord-Landwehr, T., & Haeb-Umbach, R. (2024). Once more
Diarization: Improving meeting transcription systems through segment-level speaker
reassignment. Interspeech 2024. https://doi.org/10.21437/interspeech.2024-1286'
bibtex: '@inproceedings{Boeddeker_Cord-Landwehr_Haeb-Umbach_2024, title={Once more
Diarization: Improving meeting transcription systems through segment-level speaker
reassignment}, DOI={10.21437/interspeech.2024-1286},
booktitle={Interspeech 2024}, publisher={ISCA}, author={Boeddeker, Christoph and
Cord-Landwehr, Tobias and Haeb-Umbach, Reinhold}, year={2024} }'
chicago: 'Boeddeker, Christoph, Tobias Cord-Landwehr, and Reinhold Haeb-Umbach.
“Once More Diarization: Improving Meeting Transcription Systems through Segment-Level
Speaker Reassignment.” In Interspeech 2024. ISCA, 2024. https://doi.org/10.21437/interspeech.2024-1286.'
ieee: 'C. Boeddeker, T. Cord-Landwehr, and R. Haeb-Umbach, “Once more Diarization:
Improving meeting transcription systems through segment-level speaker reassignment,”
2024, doi: 10.21437/interspeech.2024-1286.'
mla: 'Boeddeker, Christoph, et al. “Once More Diarization: Improving Meeting Transcription
Systems through Segment-Level Speaker Reassignment.” Interspeech 2024,
ISCA, 2024, doi:10.21437/interspeech.2024-1286.'
short: 'C. Boeddeker, T. Cord-Landwehr, R. Haeb-Umbach, in: Interspeech 2024, ISCA,
2024.'
date_created: 2024-09-30T08:04:47Z
date_updated: 2025-02-12T09:18:36Z
department:
- _id: '54'
doi: 10.21437/interspeech.2024-1286
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://www.isca-archive.org/interspeech_2024/boeddeker24_interspeech.pdf
oa: '1'
project:
- _id: '52'
name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing'
- _id: '508'
grant_number: '448568305'
name: Automatische Transkription von Gesprächssituationen
publication: Interspeech 2024
publication_status: published
publisher: ISCA
status: public
title: 'Once more Diarization: Improving meeting transcription systems through segment-level
speaker reassignment'
type: conference
user_id: '40767'
year: '2024'
...
---
_id: '57659'
author:
- first_name: Peter
full_name: Vieting, Peter
last_name: Vieting
- first_name: Simon
full_name: Berger, Simon
last_name: Berger
- first_name: Thilo
full_name: von Neumann, Thilo
id: '49870'
last_name: von Neumann
orcid: https://orcid.org/0000-0002-7717-8670
- first_name: Christoph
full_name: Boeddeker, Christoph
id: '40767'
last_name: Boeddeker
- first_name: Ralf
full_name: Schlüter, Ralf
last_name: Schlüter
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Vieting P, Berger S, von Neumann T, Boeddeker C, Schlüter R, Haeb-Umbach R.
Combining TF-GridNet and Mixture Encoder for Continuous Speech Separation for
Meeting Transcription. In: 2024 IEEE Spoken Language Technology Workshop (SLT).
; 2024.'
apa: Vieting, P., Berger, S., von Neumann, T., Boeddeker, C., Schlüter, R., &
Haeb-Umbach, R. (2024). Combining TF-GridNet and Mixture Encoder for Continuous
Speech Separation for Meeting Transcription. 2024 IEEE Spoken Language Technology
Workshop (SLT).
bibtex: '@inproceedings{Vieting_Berger_von Neumann_Boeddeker_Schlüter_Haeb-Umbach_2024,
title={Combining TF-GridNet and Mixture Encoder for Continuous Speech Separation
for Meeting Transcription}, booktitle={2024 IEEE Spoken Language Technology Workshop
(SLT)}, author={Vieting, Peter and Berger, Simon and von Neumann, Thilo and Boeddeker,
Christoph and Schlüter, Ralf and Haeb-Umbach, Reinhold}, year={2024} }'
chicago: Vieting, Peter, Simon Berger, Thilo von Neumann, Christoph Boeddeker, Ralf
Schlüter, and Reinhold Haeb-Umbach. “Combining TF-GridNet and Mixture Encoder
for Continuous Speech Separation for Meeting Transcription.” In 2024 IEEE Spoken
Language Technology Workshop (SLT), 2024.
ieee: P. Vieting, S. Berger, T. von Neumann, C. Boeddeker, R. Schlüter, and R. Haeb-Umbach,
“Combining TF-GridNet and Mixture Encoder for Continuous Speech Separation for
Meeting Transcription,” 2024.
mla: Vieting, Peter, et al. “Combining TF-GridNet and Mixture Encoder for Continuous
Speech Separation for Meeting Transcription.” 2024 IEEE Spoken Language Technology
Workshop (SLT), 2024.
short: 'P. Vieting, S. Berger, T. von Neumann, C. Boeddeker, R. Schlüter, R. Haeb-Umbach,
in: 2024 IEEE Spoken Language Technology Workshop (SLT), 2024.'
date_created: 2024-12-09T11:46:18Z
date_updated: 2025-02-12T09:20:59Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://www-i6.informatik.rwth-aachen.de/publications/download/1259/VietingPeterBergerSimonNeumannThilovonBoeddekerChristophSchl%FCterRalfHaeb-UmbachReinhold--CombiningTF-GridNetMixtureEncoderforContinuousSpeechSeparationforMeetingTranscription--2024.pdf
oa: '1'
project:
- _id: '52'
name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing'
- _id: '508'
grant_number: '448568305'
name: Automatische Transkription von Gesprächssituationen
publication: 2024 IEEE Spoken Language Technology Workshop (SLT)
status: public
title: Combining TF-GridNet and Mixture Encoder for Continuous Speech Separation for
Meeting Transcription
type: conference
user_id: '40767'
year: '2024'
...
---
_id: '57085'
abstract:
- lang: eng
text: We propose an approach for simultaneous diarization and separation of meeting
data. It consists of a complex Angular Central Gaussian Mixture Model (cACGMM)
for speech source separation, and a von-Mises-Fisher Mixture Model (VMFMM) for
diarization in a joint statistical framework. Through the integration, both spatial
and spectral information are exploited for diarization and separation. We also
develop a method for counting the number of active speakers in a segment of a
meeting to support block-wise processing. While the total number of speakers in
a meeting may be known, it is usually not known on a per-segment level. With the
proposed speaker counting, joint diarization and source separation can be done
segment-by-segment, and the permutation problem across segments is solved, thus
allowing for block-online processing in the future. Experimental results on the
LibriCSS meeting corpus show that the integrated approach outperforms a cascaded
approach of diarization and speech enhancement in terms of WER, both on a per-segment
and on a per-meeting level.
author:
- first_name: Tobias
full_name: Cord-Landwehr, Tobias
id: '44393'
last_name: Cord-Landwehr
- first_name: Christoph
full_name: Boeddeker, Christoph
id: '40767'
last_name: Boeddeker
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Cord-Landwehr T, Boeddeker C, Haeb-Umbach R. Simultaneous Diarization and
Separation of Meetings through the Integration of Statistical Mixture Models.
In: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and
Signal Processing (ICASSP). ; 2024. doi:10.1109/ICASSP49660.2025.10888445'
apa: Cord-Landwehr, T., Boeddeker, C., & Haeb-Umbach, R. (2024). Simultaneous
Diarization and Separation of Meetings through the Integration of Statistical
Mixture Models. ICASSP 2025 - 2025 IEEE International Conference on Acoustics,
Speech and Signal Processing (ICASSP). 2025 IEEE International Conference
on Acoustics, Speech and Signal Processing (ICASSP), Hyderabad, India. https://doi.org/10.1109/ICASSP49660.2025.10888445
bibtex: '@inproceedings{Cord-Landwehr_Boeddeker_Haeb-Umbach_2024, title={Simultaneous
Diarization and Separation of Meetings through the Integration of Statistical
Mixture Models}, DOI={10.1109/ICASSP49660.2025.10888445},
booktitle={ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech
and Signal Processing (ICASSP)}, author={Cord-Landwehr, Tobias and Boeddeker,
Christoph and Haeb-Umbach, Reinhold}, year={2024} }'
chicago: Cord-Landwehr, Tobias, Christoph Boeddeker, and Reinhold Haeb-Umbach. “Simultaneous
Diarization and Separation of Meetings through the Integration of Statistical
Mixture Models.” In ICASSP 2025 - 2025 IEEE International Conference on Acoustics,
Speech and Signal Processing (ICASSP), 2024. https://doi.org/10.1109/ICASSP49660.2025.10888445.
ieee: 'T. Cord-Landwehr, C. Boeddeker, and R. Haeb-Umbach, “Simultaneous Diarization
and Separation of Meetings through the Integration of Statistical Mixture Models,”
presented at the 2025 IEEE International Conference on Acoustics, Speech and Signal
Processing (ICASSP), Hyderabad, India, 2024, doi: 10.1109/ICASSP49660.2025.10888445.'
mla: Cord-Landwehr, Tobias, et al. “Simultaneous Diarization and Separation of Meetings
through the Integration of Statistical Mixture Models.” ICASSP 2025 - 2025
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),
2024, doi:10.1109/ICASSP49660.2025.10888445.
short: 'T. Cord-Landwehr, C. Boeddeker, R. Haeb-Umbach, in: ICASSP 2025 - 2025 IEEE
International Conference on Acoustics, Speech and Signal Processing (ICASSP),
2024.'
conference:
location: Hyderabad, India
name: 2025 IEEE International Conference on Acoustics, Speech and Signal Processing
(ICASSP)
date_created: 2024-11-14T09:32:38Z
date_updated: 2025-08-14T08:12:22Z
ddc:
- '000'
department:
- _id: '54'
doi: 10.1109/ICASSP49660.2025.10888445
file:
- access_level: closed
content_type: application/pdf
creator: cord
date_created: 2025-08-14T08:11:57Z
date_updated: 2025-08-14T08:11:57Z
file_id: '60930'
file_name: main.pdf
file_size: 259907
relation: main_file
success: 1
file_date_updated: 2025-08-14T08:11:57Z
has_accepted_license: '1'
keyword:
- diarization
- source separation
- mixture model
- meeting
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://arxiv.org/pdf/2410.21455
oa: '1'
project:
- _id: '52'
name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing'
- _id: '508'
name: Automatische Transkription von Gesprächssituationen
publication: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech
and Signal Processing (ICASSP)
status: public
title: Simultaneous Diarization and Separation of Meetings through the Integration
of Statistical Mixture Models
type: conference
user_id: '44393'
year: '2024'
...
---
_id: '53659'
author:
- first_name: Tobias
full_name: Cord-Landwehr, Tobias
id: '44393'
last_name: Cord-Landwehr
- first_name: Christoph
full_name: Boeddeker, Christoph
id: '40767'
last_name: Boeddeker
- first_name: Cătălin
full_name: Zorilă, Cătălin
last_name: Zorilă
- first_name: Rama
full_name: Doddipatla, Rama
last_name: Doddipatla
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Cord-Landwehr T, Boeddeker C, Zorilă C, Doddipatla R, Haeb-Umbach R. Geodesic
Interpolation of Frame-Wise Speaker Embeddings for the Diarization of Meeting
Scenarios. In: ICASSP 2024 - 2024 IEEE International Conference on Acoustics,
Speech and Signal Processing (ICASSP). IEEE; 2024. doi:10.1109/icassp48485.2024.10445911'
apa: Cord-Landwehr, T., Boeddeker, C., Zorilă, C., Doddipatla, R., & Haeb-Umbach,
R. (2024). Geodesic Interpolation of Frame-Wise Speaker Embeddings for the Diarization
of Meeting Scenarios. ICASSP 2024 - 2024 IEEE International Conference on Acoustics,
Speech and Signal Processing (ICASSP). 2024 IEEE International Conference
on Acoustics, Speech, and Signal Processing (ICASSP), Seoul. https://doi.org/10.1109/icassp48485.2024.10445911
bibtex: '@inproceedings{Cord-Landwehr_Boeddeker_Zorilă_Doddipatla_Haeb-Umbach_2024,
title={Geodesic Interpolation of Frame-Wise Speaker Embeddings for the Diarization
of Meeting Scenarios}, DOI={10.1109/icassp48485.2024.10445911},
booktitle={ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech
and Signal Processing (ICASSP)}, publisher={IEEE}, author={Cord-Landwehr, Tobias
and Boeddeker, Christoph and Zorilă, Cătălin and Doddipatla, Rama and Haeb-Umbach,
Reinhold}, year={2024} }'
chicago: Cord-Landwehr, Tobias, Christoph Boeddeker, Cătălin Zorilă, Rama Doddipatla,
and Reinhold Haeb-Umbach. “Geodesic Interpolation of Frame-Wise Speaker Embeddings
for the Diarization of Meeting Scenarios.” In ICASSP 2024 - 2024 IEEE International
Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2024.
https://doi.org/10.1109/icassp48485.2024.10445911.
ieee: 'T. Cord-Landwehr, C. Boeddeker, C. Zorilă, R. Doddipatla, and R. Haeb-Umbach,
“Geodesic Interpolation of Frame-Wise Speaker Embeddings for the Diarization of
Meeting Scenarios,” presented at the 2024 IEEE International Conference on Acoustics,
Speech, and Signal Processing (ICASSP), Seoul, 2024, doi: 10.1109/icassp48485.2024.10445911.'
mla: Cord-Landwehr, Tobias, et al. “Geodesic Interpolation of Frame-Wise Speaker
Embeddings for the Diarization of Meeting Scenarios.” ICASSP 2024 - 2024 IEEE
International Conference on Acoustics, Speech and Signal Processing (ICASSP),
IEEE, 2024, doi:10.1109/icassp48485.2024.10445911.
short: 'T. Cord-Landwehr, C. Boeddeker, C. Zorilă, R. Doddipatla, R. Haeb-Umbach,
in: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and
Signal Processing (ICASSP), IEEE, 2024.'
conference:
location: Seoul
name: 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing
(ICASSP)
date_created: 2024-04-25T12:57:22Z
date_updated: 2025-08-14T08:11:07Z
ddc:
- '000'
department:
- _id: '54'
doi: 10.1109/icassp48485.2024.10445911
file:
- access_level: closed
content_type: application/pdf
creator: cord
date_created: 2025-08-14T08:09:52Z
date_updated: 2025-08-14T08:09:52Z
file_id: '60929'
file_name: main.pdf
file_size: 254478
relation: main_file
success: 1
file_date_updated: 2025-08-14T08:09:52Z
has_accepted_license: '1'
language:
- iso: eng
project:
- _id: '52'
name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing'
- _id: '508'
name: Automatische Transkription von Gesprächssituationen
publication: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech
and Signal Processing (ICASSP)
publication_status: published
publisher: IEEE
status: public
title: Geodesic Interpolation of Frame-Wise Speaker Embeddings for the Diarization
of Meeting Scenarios
type: conference
user_id: '44393'
year: '2024'
...
---
_id: '57160'
abstract:
- lang: eng
text: Large audio tagging models are usually trained or pre-trained on AudioSet,
a dataset that encompasses a large amount of different sound classes and acoustic
environments. Knowledge distillation has emerged as a method to compress such
models without compromising their effectiveness. There are many different applications
for audio tagging, some of which require a specialization to a narrow domain of
sounds to be classified. For these scenarios, it is beneficial to distill the
large audio tagger with respect to a specific subset of sounds of interest. A
method to prune a general dataset with respect to a target dataset is presented.
By distilling with such a specialized pruned dataset, we obtain a compressed model
with better classification accuracy in the specific target domain than with target-agnostic
distillation.
author:
- first_name: Alexander
full_name: Werning, Alexander
id: '62152'
last_name: Werning
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Werning A, Haeb-Umbach R. Target-Specific Dataset Pruning for Compression
of Audio Tagging Models. In: 32nd European Signal Processing Conference (EUSIPCO
2024). ; 2024.'
apa: Werning, A., & Haeb-Umbach, R. (2024). Target-Specific Dataset Pruning
for Compression of Audio Tagging Models. 32nd European Signal Processing Conference
(EUSIPCO 2024). 32nd European Signal Processing Conference, Lyon.
bibtex: '@inproceedings{Werning_Haeb-Umbach_2024, title={Target-Specific Dataset
Pruning for Compression of Audio Tagging Models}, booktitle={32nd European Signal
Processing Conference (EUSIPCO 2024)}, author={Werning, Alexander and Haeb-Umbach,
Reinhold}, year={2024} }'
chicago: Werning, Alexander, and Reinhold Haeb-Umbach. “Target-Specific Dataset
Pruning for Compression of Audio Tagging Models.” In 32nd European Signal Processing
Conference (EUSIPCO 2024), 2024.
ieee: A. Werning and R. Haeb-Umbach, “Target-Specific Dataset Pruning for Compression
of Audio Tagging Models,” presented at the 32nd European Signal Processing Conference,
Lyon, 2024.
mla: Werning, Alexander, and Reinhold Haeb-Umbach. “Target-Specific Dataset Pruning
for Compression of Audio Tagging Models.” 32nd European Signal Processing Conference
(EUSIPCO 2024), 2024.
short: 'A. Werning, R. Haeb-Umbach, in: 32nd European Signal Processing Conference
(EUSIPCO 2024), 2024.'
conference:
location: Lyon
name: 32nd European Signal Processing Conference
date_created: 2024-11-18T09:29:16Z
date_updated: 2025-11-28T13:22:00Z
ddc:
- '000'
department:
- _id: '54'
file:
- access_level: closed
content_type: application/pdf
creator: awerning
date_created: 2024-11-18T12:10:09Z
date_updated: 2024-11-18T12:10:09Z
file_id: '57200'
file_name: Eusipco__Target_specific_Dataset_Pruning_for_Compression_of_Audio_Tagging_Models.pdf
file_size: 183539
relation: main_file
success: 1
file_date_updated: 2024-11-18T12:10:09Z
has_accepted_license: '1'
keyword:
- data pruning
- knowledge distillation
- audio tagging
language:
- iso: eng
project:
- _id: '512'
name: WestAI - AI Service Center West
publication: 32nd European Signal Processing Conference (EUSIPCO 2024)
quality_controlled: '1'
status: public
title: Target-Specific Dataset Pruning for Compression of Audio Tagging Models
type: conference
user_id: '62152'
year: '2024'
...
---
_id: '57031'
author:
- first_name: Tobias
full_name: Gburrek, Tobias
id: '44006'
last_name: Gburrek
- first_name: Adrian Tobias
full_name: Meise, Adrian Tobias
id: '79268'
last_name: Meise
- 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: 'Gburrek T, Meise AT, Schmalenstroeer J, Haeb-Umbach R. Diminishing Domain
Mismatch for DNN-Based Acoustic Distance Estimation via Stochastic Room Reverberation
Models. In: 2024 18th International Workshop on Acoustic Signal Enhancement
(IWAENC). IEEE; 2024. doi:10.1109/iwaenc61483.2024.10694103'
apa: Gburrek, T., Meise, A. T., Schmalenstroeer, J., & Haeb-Umbach, R. (2024).
Diminishing Domain Mismatch for DNN-Based Acoustic Distance Estimation via Stochastic
Room Reverberation Models. 2024 18th International Workshop on Acoustic Signal
Enhancement (IWAENC). https://doi.org/10.1109/iwaenc61483.2024.10694103
bibtex: '@inproceedings{Gburrek_Meise_Schmalenstroeer_Haeb-Umbach_2024, title={Diminishing
Domain Mismatch for DNN-Based Acoustic Distance Estimation via Stochastic Room
Reverberation Models}, DOI={10.1109/iwaenc61483.2024.10694103},
booktitle={2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)},
publisher={IEEE}, author={Gburrek, Tobias and Meise, Adrian Tobias and Schmalenstroeer,
Joerg and Haeb-Umbach, Reinhold}, year={2024} }'
chicago: Gburrek, Tobias, Adrian Tobias Meise, Joerg Schmalenstroeer, and Reinhold
Haeb-Umbach. “Diminishing Domain Mismatch for DNN-Based Acoustic Distance Estimation
via Stochastic Room Reverberation Models.” In 2024 18th International Workshop
on Acoustic Signal Enhancement (IWAENC). IEEE, 2024. https://doi.org/10.1109/iwaenc61483.2024.10694103.
ieee: 'T. Gburrek, A. T. Meise, J. Schmalenstroeer, and R. Haeb-Umbach, “Diminishing
Domain Mismatch for DNN-Based Acoustic Distance Estimation via Stochastic Room
Reverberation Models,” 2024, doi: 10.1109/iwaenc61483.2024.10694103.'
mla: Gburrek, Tobias, et al. “Diminishing Domain Mismatch for DNN-Based Acoustic
Distance Estimation via Stochastic Room Reverberation Models.” 2024 18th International
Workshop on Acoustic Signal Enhancement (IWAENC), IEEE, 2024, doi:10.1109/iwaenc61483.2024.10694103.
short: 'T. Gburrek, A.T. Meise, J. Schmalenstroeer, R. Haeb-Umbach, in: 2024 18th
International Workshop on Acoustic Signal Enhancement (IWAENC), IEEE, 2024.'
date_created: 2024-11-13T08:39:57Z
date_updated: 2026-01-05T16:28:23Z
ddc:
- '006'
department:
- _id: '54'
doi: 10.1109/iwaenc61483.2024.10694103
file:
- access_level: open_access
content_type: application/pdf
creator: tgburrek
date_created: 2024-11-13T08:42:13Z
date_updated: 2024-11-13T08:42:13Z
file_id: '57033'
file_name: dist_est_iwaenc24_gburrek.pdf
file_size: 300589
relation: main_file
file_date_updated: 2024-11-13T08:42:13Z
has_accepted_license: '1'
language:
- iso: eng
oa: '1'
publication: 2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)
publication_status: published
publisher: IEEE
quality_controlled: '1'
status: public
title: Diminishing Domain Mismatch for DNN-Based Acoustic Distance Estimation via
Stochastic Room Reverberation Models
type: conference
user_id: '44006'
year: '2024'
...
---
_id: '48269'
author:
- first_name: Tobias
full_name: Gburrek, Tobias
id: '44006'
last_name: Gburrek
- 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: 'Gburrek T, Schmalenstroeer J, Haeb-Umbach R. On the Integration of Sampling
Rate Synchronization and Acoustic Beamforming. In: European Signal Processing
Conference (EUSIPCO). ; 2023.'
apa: Gburrek, T., Schmalenstroeer, J., & Haeb-Umbach, R. (2023). On the Integration
of Sampling Rate Synchronization and Acoustic Beamforming. European Signal
Processing Conference (EUSIPCO). European Signal Processing Conference (EUSIPCO),
Helsinki.
bibtex: '@inproceedings{Gburrek_Schmalenstroeer_Haeb-Umbach_2023, title={On the
Integration of Sampling Rate Synchronization and Acoustic Beamforming}, booktitle={European
Signal Processing Conference (EUSIPCO)}, author={Gburrek, Tobias and Schmalenstroeer,
Joerg and Haeb-Umbach, Reinhold}, year={2023} }'
chicago: Gburrek, Tobias, Joerg Schmalenstroeer, and Reinhold Haeb-Umbach. “On the
Integration of Sampling Rate Synchronization and Acoustic Beamforming.” In European
Signal Processing Conference (EUSIPCO), 2023.
ieee: T. Gburrek, J. Schmalenstroeer, and R. Haeb-Umbach, “On the Integration of
Sampling Rate Synchronization and Acoustic Beamforming,” presented at the European
Signal Processing Conference (EUSIPCO), Helsinki, 2023.
mla: Gburrek, Tobias, et al. “On the Integration of Sampling Rate Synchronization
and Acoustic Beamforming.” European Signal Processing Conference (EUSIPCO),
2023.
short: 'T. Gburrek, J. Schmalenstroeer, R. Haeb-Umbach, in: European Signal Processing
Conference (EUSIPCO), 2023.'
conference:
location: Helsinki
name: European Signal Processing Conference (EUSIPCO)
date_created: 2023-10-18T12:54:08Z
date_updated: 2023-10-26T08:16:23Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://eurasip.org/Proceedings/Eusipco/Eusipco2023/pdfs/0000011.pdf
oa: '1'
publication: European Signal Processing Conference (EUSIPCO)
quality_controlled: '1'
status: public
title: On the Integration of Sampling Rate Synchronization and Acoustic Beamforming
type: conference
user_id: '460'
year: '2023'
...
---
_id: '48270'
author:
- first_name: Joerg
full_name: Schmalenstroeer, Joerg
id: '460'
last_name: Schmalenstroeer
- first_name: Tobias
full_name: Gburrek, Tobias
id: '44006'
last_name: Gburrek
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Schmalenstroeer J, Gburrek T, Haeb-Umbach R. LibriWASN: A Data Set for Meeting
Separation, Diarization, and Recognition with Asynchronous Recording Devices.
In: ITG Conference on Speech Communication. ; 2023.'
apa: 'Schmalenstroeer, J., Gburrek, T., & Haeb-Umbach, R. (2023). LibriWASN:
A Data Set for Meeting Separation, Diarization, and Recognition with Asynchronous
Recording Devices. ITG Conference on Speech Communication. ITG Conference
on Speech Communication, Aachen.'
bibtex: '@inproceedings{Schmalenstroeer_Gburrek_Haeb-Umbach_2023, title={LibriWASN:
A Data Set for Meeting Separation, Diarization, and Recognition with Asynchronous
Recording Devices}, booktitle={ITG Conference on Speech Communication}, author={Schmalenstroeer,
Joerg and Gburrek, Tobias and Haeb-Umbach, Reinhold}, year={2023} }'
chicago: 'Schmalenstroeer, Joerg, Tobias Gburrek, and Reinhold Haeb-Umbach. “LibriWASN:
A Data Set for Meeting Separation, Diarization, and Recognition with Asynchronous
Recording Devices.” In ITG Conference on Speech Communication, 2023.'
ieee: 'J. Schmalenstroeer, T. Gburrek, and R. Haeb-Umbach, “LibriWASN: A Data Set
for Meeting Separation, Diarization, and Recognition with Asynchronous Recording
Devices,” presented at the ITG Conference on Speech Communication, Aachen, 2023.'
mla: 'Schmalenstroeer, Joerg, et al. “LibriWASN: A Data Set for Meeting Separation,
Diarization, and Recognition with Asynchronous Recording Devices.” ITG Conference
on Speech Communication, 2023.'
short: 'J. Schmalenstroeer, T. Gburrek, R. Haeb-Umbach, in: ITG Conference on Speech
Communication, 2023.'
conference:
location: Aachen
name: ITG Conference on Speech Communication
date_created: 2023-10-18T13:00:54Z
date_updated: 2023-11-15T14:48:45Z
ddc:
- '004'
department:
- _id: '54'
file:
- access_level: open_access
content_type: application/pdf
creator: schmalen
date_created: 2023-10-26T08:20:15Z
date_updated: 2023-11-15T14:48:44Z
file_id: '48483'
file_name: SchTgbHaeb2023Final.pdf
file_size: 2844502
relation: main_file
file_date_updated: 2023-11-15T14:48:44Z
has_accepted_license: '1'
language:
- iso: eng
oa: '1'
publication: ITG Conference on Speech Communication
quality_controlled: '1'
status: public
title: 'LibriWASN: A Data Set for Meeting Separation, Diarization, and Recognition
with Asynchronous Recording Devices'
type: conference
user_id: '460'
year: '2023'
...
---
_id: '48355'
abstract:
- lang: eng
text: "Unsupervised speech disentanglement aims at separating fast varying from\r\nslowly
varying components of a speech signal. In this contribution, we take a\r\ncloser
look at the embedding vector representing the slowly varying signal\r\ncomponents,
commonly named the speaker embedding vector. We ask, which\r\nproperties of a
speaker's voice are captured and investigate to which extent do\r\nindividual
embedding vector components sign responsible for them, using the\r\nconcept of
Shapley values. Our findings show that certain speaker-specific\r\nacoustic-phonetic
properties can be fairly well predicted from the speaker\r\nembedding, while the
investigated more abstract voice quality features cannot."
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: 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, Wiechmann J, Seebauer F, Wagner P, Haeb-Umbach R.
On Feature Importance and Interpretability of Speaker Representations. In: ITG
Conference on Speech Communication. ; 2023.'
apa: Rautenberg, F., Kuhlmann, M., Wiechmann, J., Seebauer, F., Wagner, P., &
Haeb-Umbach, R. (2023). On Feature Importance and Interpretability of Speaker
Representations. ITG Conference on Speech Communication. ITG Conference
on Speech Communication, Aachen.
bibtex: '@inproceedings{Rautenberg_Kuhlmann_Wiechmann_Seebauer_Wagner_Haeb-Umbach_2023,
title={On Feature Importance and Interpretability of Speaker Representations},
booktitle={ITG Conference on Speech Communication}, author={Rautenberg, Frederik
and Kuhlmann, Michael and Wiechmann, Jana and Seebauer, Fritz and Wagner, Petra
and Haeb-Umbach, Reinhold}, year={2023} }'
chicago: Rautenberg, Frederik, Michael Kuhlmann, Jana Wiechmann, Fritz Seebauer,
Petra Wagner, and Reinhold Haeb-Umbach. “On Feature Importance and Interpretability
of Speaker Representations.” In ITG Conference on Speech Communication,
2023.
ieee: F. Rautenberg, M. Kuhlmann, J. Wiechmann, F. Seebauer, P. Wagner, and R. Haeb-Umbach,
“On Feature Importance and Interpretability of Speaker Representations,” presented
at the ITG Conference on Speech Communication, Aachen, 2023.
mla: Rautenberg, Frederik, et al. “On Feature Importance and Interpretability of
Speaker Representations.” ITG Conference on Speech Communication, 2023.
short: 'F. Rautenberg, M. Kuhlmann, J. Wiechmann, F. Seebauer, P. Wagner, R. Haeb-Umbach,
in: ITG Conference on Speech Communication, 2023.'
conference:
end_date: 2023-09-22
location: Aachen
name: ITG Conference on Speech Communication
start_date: 2023-09-20
date_created: 2023-10-20T08:04:46Z
date_updated: 2023-11-22T13:44:33Z
ddc:
- '000'
department:
- _id: '54'
- _id: '660'
external_id:
arxiv:
- '2310.12599'
file:
- access_level: closed
content_type: application/pdf
creator: frra
date_created: 2023-10-20T08:20:58Z
date_updated: 2023-10-20T08:20:58Z
file_id: '48359'
file_name: arxiv.pdf
file_size: 272390
relation: main_file
success: 1
file_date_updated: 2023-10-20T08:20:58Z
has_accepted_license: '1'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://arxiv.org/abs/2310.12599
oa: '1'
project:
- _id: '129'
grant_number: '438445824'
name: 'TRR 318 - C06: TRR 318 - Technisch unterstütztes Erklären von Stimmcharakteristika
(Teilprojekt C06)'
publication: ITG Conference on Speech Communication
status: public
title: On Feature Importance and Interpretability of Speaker Representations
type: conference
user_id: '72602'
year: '2023'
...