---
_id: '65606'
abstract:
- lang: eng
  text: Sound capture by microphone arrays opens the possibility to exploit spatial,
    in addition to spectral, information for diarization and signal enhancement, two
    important tasks in meeting transcription. However, there is no one-to-one mapping
    of positions in space to speakers if speakers move. Here, we address this by proposing
    a novel joint spatial and spectral mixture model, whose two submodels are loosely
    coupled by modeling the relationship between speaker and position index probabilistically.
    Thus, spatial and spectral information can be jointly exploited, while at the
    same time allowing for speakers speaking from different positions. Experiments
    on the LibriCSS data set with simulated speaker position changes show great improvements
    over tightly coupled subsystems.
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: Christoph
  full_name: Boeddeker, Christoph
  id: '40767'
  last_name: Boeddeker
- first_name: Marc
  full_name: Delcroix, Marc
  last_name: Delcroix
- first_name: Tomohiro
  full_name: Nakatani, Tomohiro
  last_name: Nakatani
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: 'Meise AT, Cord-Landwehr T, Boeddeker C, Delcroix M, Nakatani T, Haeb-Umbach
    R. Loose Coupling of Spectral and Spatial Models for Multi-Channel Diarization
    and Enhancement of Meetings in Dynamic Environments. In: <i>ICASSP 2026 - 2026
    IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>.
    IEEE; 2026. doi:<a href="https://doi.org/10.1109/icassp55912.2026.11463540">10.1109/icassp55912.2026.11463540</a>'
  apa: Meise, A. T., Cord-Landwehr, T., Boeddeker, C., Delcroix, M., Nakatani, T.,
    &#38; Haeb-Umbach, R. (2026). Loose Coupling of Spectral and Spatial Models for
    Multi-Channel Diarization and Enhancement of Meetings in Dynamic Environments.
    <i>ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal
    Processing (ICASSP)</i>.  2026 IEEE International Conference on Acoustics, Speech
    and Signal Processing (ICASSP) , Barcelona. <a href="https://doi.org/10.1109/icassp55912.2026.11463540">https://doi.org/10.1109/icassp55912.2026.11463540</a>
  bibtex: '@inproceedings{Meise_Cord-Landwehr_Boeddeker_Delcroix_Nakatani_Haeb-Umbach_2026,
    title={Loose Coupling of Spectral and Spatial Models for Multi-Channel Diarization
    and Enhancement of Meetings in Dynamic Environments}, DOI={<a href="https://doi.org/10.1109/icassp55912.2026.11463540">10.1109/icassp55912.2026.11463540</a>},
    booktitle={ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech
    and Signal Processing (ICASSP)}, publisher={IEEE}, author={Meise, Adrian Tobias
    and Cord-Landwehr, Tobias and Boeddeker, Christoph and Delcroix, Marc and Nakatani,
    Tomohiro and Haeb-Umbach, Reinhold}, year={2026} }'
  chicago: Meise, Adrian Tobias, Tobias Cord-Landwehr, Christoph Boeddeker, Marc Delcroix,
    Tomohiro Nakatani, and Reinhold Haeb-Umbach. “Loose Coupling of Spectral and Spatial
    Models for Multi-Channel Diarization and Enhancement of Meetings in Dynamic Environments.”
    In <i>ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and
    Signal Processing (ICASSP)</i>. IEEE, 2026. <a href="https://doi.org/10.1109/icassp55912.2026.11463540">https://doi.org/10.1109/icassp55912.2026.11463540</a>.
  ieee: 'A. T. Meise, T. Cord-Landwehr, C. Boeddeker, M. Delcroix, T. Nakatani, and
    R. Haeb-Umbach, “Loose Coupling of Spectral and Spatial Models for Multi-Channel
    Diarization and Enhancement of Meetings in Dynamic Environments,” presented at
    the  2026 IEEE International Conference on Acoustics, Speech and Signal Processing
    (ICASSP) , Barcelona, 2026, doi: <a href="https://doi.org/10.1109/icassp55912.2026.11463540">10.1109/icassp55912.2026.11463540</a>.'
  mla: Meise, Adrian Tobias, et al. “Loose Coupling of Spectral and Spatial Models
    for Multi-Channel Diarization and Enhancement of Meetings in Dynamic Environments.”
    <i>ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal
    Processing (ICASSP)</i>, IEEE, 2026, doi:<a href="https://doi.org/10.1109/icassp55912.2026.11463540">10.1109/icassp55912.2026.11463540</a>.
  short: 'A.T. Meise, T. Cord-Landwehr, C. Boeddeker, M. Delcroix, T. Nakatani, R.
    Haeb-Umbach, in: ICASSP 2026 - 2026 IEEE International Conference on Acoustics,
    Speech and Signal Processing (ICASSP), IEEE, 2026.'
conference:
  location: Barcelona
  name: ' 2026 IEEE International Conference on Acoustics, Speech and Signal Processing
    (ICASSP) '
date_created: 2026-05-11T14:20:48Z
date_updated: 2026-05-15T08:17:25Z
department:
- _id: '54'
- _id: '1063'
doi: 10.1109/icassp55912.2026.11463540
external_id:
  arxiv:
  - https://arxiv.org/abs/2601.16077
keyword:
- mixture models
- meeting processing
- diarization
- source separation
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://arxiv.org/pdf/2601.16077
oa: '1'
project:
- _id: '52'
  name: Computing Resources Provided by the Paderborn Center for Parallel Computing
publication: ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech
  and Signal Processing (ICASSP)
publisher: IEEE
status: public
title: Loose Coupling of Spectral and Spatial Models for Multi-Channel Diarization
  and Enhancement of Meetings in Dynamic Environments
type: conference
user_id: '79268'
year: '2026'
...
---
_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: <i> ITG Conference
    on Speech Communication</i>. ; 2025.'
  apa: Meise, A. T., Cord-Landwehr, T., &#38; Haeb-Umbach, R. (2025). On the Application
    of Diffusion Models for Simultaneous Denoising and Dereverberation. <i> ITG Conference
    on Speech Communication</i>. 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 <i> ITG Conference on Speech Communication</i>, 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.” <i> ITG Conference on Speech Communication</i>,
    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: '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: <i>2024 18th International Workshop on Acoustic Signal Enhancement
    (IWAENC)</i>. IEEE; 2024. doi:<a href="https://doi.org/10.1109/iwaenc61483.2024.10694103">10.1109/iwaenc61483.2024.10694103</a>'
  apa: Gburrek, T., Meise, A. T., Schmalenstroeer, J., &#38; Haeb-Umbach, R. (2024).
    Diminishing Domain Mismatch for DNN-Based Acoustic Distance Estimation via Stochastic
    Room Reverberation Models. <i>2024 18th International Workshop on Acoustic Signal
    Enhancement (IWAENC)</i>. <a href="https://doi.org/10.1109/iwaenc61483.2024.10694103">https://doi.org/10.1109/iwaenc61483.2024.10694103</a>
  bibtex: '@inproceedings{Gburrek_Meise_Schmalenstroeer_Haeb-Umbach_2024, title={Diminishing
    Domain Mismatch for DNN-Based Acoustic Distance Estimation via Stochastic Room
    Reverberation Models}, DOI={<a href="https://doi.org/10.1109/iwaenc61483.2024.10694103">10.1109/iwaenc61483.2024.10694103</a>},
    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 <i>2024 18th International Workshop
    on Acoustic Signal Enhancement (IWAENC)</i>. IEEE, 2024. <a href="https://doi.org/10.1109/iwaenc61483.2024.10694103">https://doi.org/10.1109/iwaenc61483.2024.10694103</a>.
  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: <a href="https://doi.org/10.1109/iwaenc61483.2024.10694103">10.1109/iwaenc61483.2024.10694103</a>.'
  mla: Gburrek, Tobias, et al. “Diminishing Domain Mismatch for DNN-Based Acoustic
    Distance Estimation via Stochastic Room Reverberation Models.” <i>2024 18th International
    Workshop on Acoustic Signal Enhancement (IWAENC)</i>, IEEE, 2024, doi:<a href="https://doi.org/10.1109/iwaenc61483.2024.10694103">10.1109/iwaenc61483.2024.10694103</a>.
  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: '57086'
author:
- first_name: Michael
  full_name: Kuhlmann, Michael
  id: '49871'
  last_name: Kuhlmann
- first_name: Adrian Tobias
  full_name: Meise, Adrian Tobias
  id: '79268'
  last_name: Meise
- 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: Häb-Umbach, Reinhold
  id: '242'
  last_name: Häb-Umbach
citation:
  ama: 'Kuhlmann M, Meise AT, Seebauer F, Wagner P, Häb-Umbach R. Investigating Speaker
    Embedding Disentanglement on Natural Read Speech. In: <i>Speech Communication;
    15th ITG Conference</i>. ; 2023:121–125.'
  apa: Kuhlmann, M., Meise, A. T., Seebauer, F., Wagner, P., &#38; Häb-Umbach, R.
    (2023). Investigating Speaker Embedding Disentanglement on Natural Read Speech.
    <i>Speech Communication; 15th ITG Conference</i>, 121–125.
  bibtex: '@inproceedings{Kuhlmann_Meise_Seebauer_Wagner_Häb-Umbach_2023, title={Investigating
    Speaker Embedding Disentanglement on Natural Read Speech}, booktitle={Speech Communication;
    15th ITG Conference}, author={Kuhlmann, Michael and Meise, Adrian Tobias and Seebauer,
    Fritz and Wagner, Petra and Häb-Umbach, Reinhold}, year={2023}, pages={121–125}
    }'
  chicago: Kuhlmann, Michael, Adrian Tobias Meise, Fritz Seebauer, Petra Wagner, and
    Reinhold Häb-Umbach. “Investigating Speaker Embedding Disentanglement on Natural
    Read Speech.” In <i>Speech Communication; 15th ITG Conference</i>, 121–125, 2023.
  ieee: M. Kuhlmann, A. T. Meise, F. Seebauer, P. Wagner, and R. Häb-Umbach, “Investigating
    Speaker Embedding Disentanglement on Natural Read Speech,” in <i>Speech Communication;
    15th ITG Conference</i>, 2023, pp. 121–125.
  mla: Kuhlmann, Michael, et al. “Investigating Speaker Embedding Disentanglement
    on Natural Read Speech.” <i>Speech Communication; 15th ITG Conference</i>, 2023,
    pp. 121–125.
  short: 'M. Kuhlmann, A.T. Meise, F. Seebauer, P. Wagner, R. Häb-Umbach, in: Speech
    Communication; 15th ITG Conference, 2023, pp. 121–125.'
date_created: 2024-11-14T09:45:03Z
date_updated: 2026-01-05T10:12:23Z
department:
- _id: '54'
language:
- iso: eng
page: 121–125
project:
- _id: '52'
  name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing'
publication: Speech Communication; 15th ITG Conference
status: public
title: Investigating Speaker Embedding Disentanglement on Natural Read Speech
type: conference
user_id: '49871'
year: '2023'
...