---
_id: '35602'
abstract:
- lang: eng
  text: "Continuous Speech Separation (CSS) has been proposed to address speech overlaps
    during the analysis of realistic meeting-like conversations by eliminating any
    overlaps before further processing.\r\nCSS separates a recording of arbitrarily
    many speakers into a small number of overlap-free output channels, where each
    output channel may contain speech of multiple speakers.\r\nThis is often done
    by applying a conventional separation model trained with Utterance-level Permutation
    Invariant Training (uPIT), which exclusively maps a speaker to an output channel,
    in sliding window approach called stitching.\r\nRecently, we introduced an alternative
    training scheme called Graph-PIT that teaches the separation network to directly
    produce output streams in the required format without stitching.\r\nIt can handle
    an arbitrary number of speakers as long as never more of them overlap at the same
    time than the separator has output channels.\r\nIn this contribution, we further
    investigate the Graph-PIT training scheme.\r\nWe show in extended experiments
    that models trained with Graph-PIT also work in challenging reverberant conditions.\r\nModels
    trained in this way are able to perform segment-less CSS, i.e., without stitching,
    and achieve comparable and often better separation quality than the conventional
    CSS with uPIT and stitching.\r\nWe simplify the training schedule for Graph-PIT
    with the recently proposed Source Aggregated Signal-to-Distortion Ratio (SA-SDR)
    loss.\r\nIt eliminates unfavorable properties of the previously used A-SDR loss
    and thus enables training with Graph-PIT from scratch.\r\nGraph-PIT training relaxes
    the constraints w.r.t. the allowed numbers of speakers and speaking patterns which
    allows using a larger variety of training data.\r\nFurthermore, we introduce novel
    signal-level evaluation metrics for meeting scenarios, namely the source-aggregated
    scale- and convolution-invariant Signal-to-Distortion Ratio (SA-SI-SDR and SA-CI-SDR),
    which are generalizations of the commonly used SDR-based metrics for the CSS case."
article_type: original
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: Keisuke
  full_name: Kinoshita, Keisuke
  last_name: Kinoshita
- first_name: Christoph
  full_name: Boeddeker, Christoph
  id: '40767'
  last_name: Boeddeker
- 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, Kinoshita K, Boeddeker C, Delcroix M, Haeb-Umbach R. Segment-Less
    Continuous Speech Separation of Meetings: Training and Evaluation Criteria. <i>IEEE/ACM
    Transactions on Audio, Speech, and Language Processing</i>. 2023;31:576-589. doi:<a
    href="https://doi.org/10.1109/taslp.2022.3228629">10.1109/taslp.2022.3228629</a>'
  apa: 'von Neumann, T., Kinoshita, K., Boeddeker, C., Delcroix, M., &#38; Haeb-Umbach,
    R. (2023). Segment-Less Continuous Speech Separation of Meetings: Training and
    Evaluation Criteria. <i>IEEE/ACM Transactions on Audio, Speech, and Language Processing</i>,
    <i>31</i>, 576–589. <a href="https://doi.org/10.1109/taslp.2022.3228629">https://doi.org/10.1109/taslp.2022.3228629</a>'
  bibtex: '@article{von Neumann_Kinoshita_Boeddeker_Delcroix_Haeb-Umbach_2023, title={Segment-Less
    Continuous Speech Separation of Meetings: Training and Evaluation Criteria}, volume={31},
    DOI={<a href="https://doi.org/10.1109/taslp.2022.3228629">10.1109/taslp.2022.3228629</a>},
    journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing}, publisher={Institute
    of Electrical and Electronics Engineers (IEEE)}, author={von Neumann, Thilo and
    Kinoshita, Keisuke and Boeddeker, Christoph and Delcroix, Marc and Haeb-Umbach,
    Reinhold}, year={2023}, pages={576–589} }'
  chicago: 'Neumann, Thilo von, Keisuke Kinoshita, Christoph Boeddeker, Marc Delcroix,
    and Reinhold Haeb-Umbach. “Segment-Less Continuous Speech Separation of Meetings:
    Training and Evaluation Criteria.” <i>IEEE/ACM Transactions on Audio, Speech,
    and Language Processing</i> 31 (2023): 576–89. <a href="https://doi.org/10.1109/taslp.2022.3228629">https://doi.org/10.1109/taslp.2022.3228629</a>.'
  ieee: 'T. von Neumann, K. Kinoshita, C. Boeddeker, M. Delcroix, and R. Haeb-Umbach,
    “Segment-Less Continuous Speech Separation of Meetings: Training and Evaluation
    Criteria,” <i>IEEE/ACM Transactions on Audio, Speech, and Language Processing</i>,
    vol. 31, pp. 576–589, 2023, doi: <a href="https://doi.org/10.1109/taslp.2022.3228629">10.1109/taslp.2022.3228629</a>.'
  mla: 'von Neumann, Thilo, et al. “Segment-Less Continuous Speech Separation of Meetings:
    Training and Evaluation Criteria.” <i>IEEE/ACM Transactions on Audio, Speech,
    and Language Processing</i>, vol. 31, Institute of Electrical and Electronics
    Engineers (IEEE), 2023, pp. 576–89, doi:<a href="https://doi.org/10.1109/taslp.2022.3228629">10.1109/taslp.2022.3228629</a>.'
  short: T. von Neumann, K. Kinoshita, C. Boeddeker, M. Delcroix, R. Haeb-Umbach,
    IEEE/ACM Transactions on Audio, Speech, and Language Processing 31 (2023) 576–589.
date_created: 2023-01-09T17:24:17Z
date_updated: 2023-11-15T12:16:11Z
ddc:
- '000'
department:
- _id: '54'
doi: 10.1109/taslp.2022.3228629
file:
- access_level: open_access
  content_type: application/pdf
  creator: haebumb
  date_created: 2023-01-09T17:46:05Z
  date_updated: 2023-01-11T08:50:19Z
  file_id: '35607'
  file_name: main.pdf
  file_size: 7185077
  relation: main_file
file_date_updated: 2023-01-11T08:50:19Z
has_accepted_license: '1'
intvolume: '        31'
keyword:
- Continuous Speech Separation
- Source Separation
- Graph-PIT
- Dynamic Programming
- Permutation Invariant Training
language:
- iso: eng
oa: '1'
page: 576-589
project:
- _id: '52'
  name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing'
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)
quality_controlled: '1'
status: public
title: 'Segment-Less Continuous Speech Separation of Meetings: Training and Evaluation
  Criteria'
type: journal_article
user_id: '49870'
volume: 31
year: '2023'
...
---
_id: '48855'
abstract:
- lang: eng
  text: Computing sets of high quality solutions has gained increasing interest in
    recent years. In this paper, we investigate how to obtain sets of optimal solutions
    for the classical knapsack problem. We present an algorithm to count exactly the
    number of optima to a zero-one knapsack problem instance. In addition, we show
    how to efficiently sample uniformly at random from the set of all global optima.
    In our experimental study, we investigate how the number of optima develops for
    classical random benchmark instances dependent on their generator parameters.
    We find that the number of global optima can increase exponentially for practically
    relevant classes of instances with correlated weights and profits which poses
    a justification for the considered exact counting problem.
author:
- first_name: Jakob
  full_name: Bossek, Jakob
  id: '102979'
  last_name: Bossek
  orcid: 0000-0002-4121-4668
- first_name: Aneta
  full_name: Neumann, Aneta
  last_name: Neumann
- first_name: Frank
  full_name: Neumann, Frank
  last_name: Neumann
citation:
  ama: 'Bossek J, Neumann A, Neumann F. Exact Counting and~Sampling of Optima for
    the Knapsack Problem. In: <i>Learning and Intelligent Optimization</i>. Springer-Verlag;
    2021:40–54. doi:<a href="https://doi.org/10.1007/978-3-030-92121-7_4">10.1007/978-3-030-92121-7_4</a>'
  apa: Bossek, J., Neumann, A., &#38; Neumann, F. (2021). Exact Counting and~Sampling
    of Optima for the Knapsack Problem. <i>Learning and Intelligent Optimization</i>,
    40–54. <a href="https://doi.org/10.1007/978-3-030-92121-7_4">https://doi.org/10.1007/978-3-030-92121-7_4</a>
  bibtex: '@inproceedings{Bossek_Neumann_Neumann_2021, place={Berlin, Heidelberg},
    title={Exact Counting and~Sampling of Optima for the Knapsack Problem}, DOI={<a
    href="https://doi.org/10.1007/978-3-030-92121-7_4">10.1007/978-3-030-92121-7_4</a>},
    booktitle={Learning and Intelligent Optimization}, publisher={Springer-Verlag},
    author={Bossek, Jakob and Neumann, Aneta and Neumann, Frank}, year={2021}, pages={40–54}
    }'
  chicago: 'Bossek, Jakob, Aneta Neumann, and Frank Neumann. “Exact Counting And~Sampling
    of Optima for the Knapsack Problem.” In <i>Learning and Intelligent Optimization</i>,
    40–54. Berlin, Heidelberg: Springer-Verlag, 2021. <a href="https://doi.org/10.1007/978-3-030-92121-7_4">https://doi.org/10.1007/978-3-030-92121-7_4</a>.'
  ieee: 'J. Bossek, A. Neumann, and F. Neumann, “Exact Counting and~Sampling of Optima
    for the Knapsack Problem,” in <i>Learning and Intelligent Optimization</i>, 2021,
    pp. 40–54, doi: <a href="https://doi.org/10.1007/978-3-030-92121-7_4">10.1007/978-3-030-92121-7_4</a>.'
  mla: Bossek, Jakob, et al. “Exact Counting And~Sampling of Optima for the Knapsack
    Problem.” <i>Learning and Intelligent Optimization</i>, Springer-Verlag, 2021,
    pp. 40–54, doi:<a href="https://doi.org/10.1007/978-3-030-92121-7_4">10.1007/978-3-030-92121-7_4</a>.
  short: 'J. Bossek, A. Neumann, F. Neumann, in: Learning and Intelligent Optimization,
    Springer-Verlag, Berlin, Heidelberg, 2021, pp. 40–54.'
date_created: 2023-11-14T15:58:54Z
date_updated: 2023-12-13T10:45:14Z
department:
- _id: '819'
doi: 10.1007/978-3-030-92121-7_4
extern: '1'
keyword:
- Dynamic programming
- Exact counting
- Sampling
- Zero-one knapsack problem
language:
- iso: eng
page: 40–54
place: Berlin, Heidelberg
publication: Learning and Intelligent Optimization
publication_identifier:
  isbn:
  - 978-3-030-92120-0
publication_status: published
publisher: Springer-Verlag
status: public
title: Exact Counting and~Sampling of Optima for the Knapsack Problem
type: conference
user_id: '102979'
year: '2021'
...
---
_id: '17651'
abstract:
- lang: eng
  text: 'Consider mitigating the effects of denial of service or of malicious traffic
    in networks by deleting edges. Edge deletion reduces the DoS or the number of
    the malicious flows, but it also inadvertently removes some of the desired flows.
    To model this important problem, we formulate two problems: (1) remove all the
    undesirable flows while minimizing the damage to the desirable ones and (2) balance
    removing the undesirable flows and not removing too many of the desirable flows.
    We prove these problems are equivalent to important theoretical problems, thereby
    being important not only practically but also theoretically, and very hard to
    approximate in a general network. We employ reductions to nonetheless approximate
    the problem and also provide a greedy approximation. When the network is a tree,
    the problems are still MAX SNP-hard, but we provide a greedy-based 2l-approximation
    algorithm, where l is the longest desirable flow. We also provide an algorithm,
    approximating the first and the second problem within {\$}{\$}2 {\backslash}sqrt{\{}
    2{\backslash}left| E {\backslash}right| {\}}{\$}{\$}and {\$}{\$}2 {\backslash}sqrt{\{}2
    ({\backslash}left| E {\backslash}right| + {\backslash}left| {\backslash}text {\{}undesirable
    flows{\}} {\backslash}right| ){\}}{\$}{\$}, respectively, where E is the set of
    the edges of the network. We also provide a fixed-parameter tractable (FPT) algorithm.
    Finally, if the tree has a root such that every flow in the tree flows on the
    path from the root to a leaf, we solve the problem exactly using dynamic programming.'
author:
- first_name: Gleb
  full_name: Polevoy, Gleb
  id: '83983'
  last_name: Polevoy
- first_name: Stojan
  full_name: Trajanovski, Stojan
  last_name: Trajanovski
- first_name: Paola
  full_name: Grosso, Paola
  last_name: Grosso
- first_name: Cees
  full_name: de Laat, Cees
  last_name: de Laat
citation:
  ama: 'Polevoy G, Trajanovski S, Grosso P, de Laat C. Removing Undesirable Flows
    by Edge Deletion. In: Kim D, Uma RN, Zelikovsky A, eds. <i>Combinatorial Optimization
    and Applications</i>. Cham: Springer International Publishing; 2018:217-232.'
  apa: 'Polevoy, G., Trajanovski, S., Grosso, P., &#38; de Laat, C. (2018). Removing
    Undesirable Flows by Edge Deletion. In D. Kim, R. N. Uma, &#38; A. Zelikovsky
    (Eds.), <i>Combinatorial Optimization and Applications</i> (pp. 217–232). Cham:
    Springer International Publishing.'
  bibtex: '@inproceedings{Polevoy_Trajanovski_Grosso_de Laat_2018, place={Cham}, title={Removing
    Undesirable Flows by Edge Deletion}, booktitle={Combinatorial Optimization and
    Applications}, publisher={Springer International Publishing}, author={Polevoy,
    Gleb and Trajanovski, Stojan and Grosso, Paola and de Laat, Cees}, editor={Kim,
    Donghyun and Uma, R. N. and Zelikovsky, AlexanderEditors}, year={2018}, pages={217–232}
    }'
  chicago: 'Polevoy, Gleb, Stojan Trajanovski, Paola Grosso, and Cees de Laat. “Removing
    Undesirable Flows by Edge Deletion.” In <i>Combinatorial Optimization and Applications</i>,
    edited by Donghyun Kim, R. N. Uma, and Alexander Zelikovsky, 217–32. Cham: Springer
    International Publishing, 2018.'
  ieee: G. Polevoy, S. Trajanovski, P. Grosso, and C. de Laat, “Removing Undesirable
    Flows by Edge Deletion,” in <i>Combinatorial Optimization and Applications</i>,
    2018, pp. 217–232.
  mla: Polevoy, Gleb, et al. “Removing Undesirable Flows by Edge Deletion.” <i>Combinatorial
    Optimization and Applications</i>, edited by Donghyun Kim et al., Springer International
    Publishing, 2018, pp. 217–32.
  short: 'G. Polevoy, S. Trajanovski, P. Grosso, C. de Laat, in: D. Kim, R.N. Uma,
    A. Zelikovsky (Eds.), Combinatorial Optimization and Applications, Springer International
    Publishing, Cham, 2018, pp. 217–232.'
date_created: 2020-08-06T15:19:36Z
date_updated: 2022-01-06T06:53:16Z
department:
- _id: '63'
- _id: '541'
editor:
- first_name: Donghyun
  full_name: Kim, Donghyun
  last_name: Kim
- first_name: R. N.
  full_name: Uma, R. N.
  last_name: Uma
- first_name: Alexander
  full_name: Zelikovsky, Alexander
  last_name: Zelikovsky
extern: '1'
keyword:
- flow
- Red-Blue Set Cover
- Positive-Negative Partial Set Cover
- approximation
- tree
- MAX SNP-hard
- root
- leaf
- dynamic programming
- FPT
language:
- iso: eng
page: 217-232
place: Cham
publication: Combinatorial Optimization and Applications
publication_identifier:
  isbn:
  - 978-3-030-04651-4
publisher: Springer International Publishing
status: public
title: Removing Undesirable Flows by Edge Deletion
type: conference
user_id: '83983'
year: '2018'
...