Dynamic Gated Recurrent Neural Network for Compute-efficient Speech Enhancement Article Swipe
Longbiao Cheng
,
Ashutosh Pandey
,
Buye Xu
,
Tobi Delbrück
,
Shih‐Chii Liu
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.21437/interspeech.2024-958
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.21437/interspeech.2024-958
This paper introduces a new Dynamic Gated Recurrent Neural Network (DG-RNN)\nfor compute-efficient speech enhancement models running on resource-constrained\nhardware platforms. It leverages the slow evolution characteristic of RNN\nhidden states over steps, and updates only a selected set of neurons at each\nstep by adding a newly proposed select gate to the RNN model. This select gate\nallows the computation cost of the conventional RNN to be reduced during\nnetwork inference. As a realization of the DG-RNN, we further propose the\nDynamic Gated Recurrent Unit (D-GRU) which does not require additional\nparameters. Test results obtained from several state-of-the-art\ncompute-efficient RNN-based speech enhancement architectures using the DNS\nchallenge dataset, show that the D-GRU based model variants maintain similar\nspeech intelligibility and quality metrics comparable to the baseline GRU based\nmodels even with an average 50% reduction in GRU computes.\n
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- https://doi.org/10.21437/interspeech.2024-958
- OA Status
- green
- Cited By
- 6
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4402112230
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4402112230Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.21437/interspeech.2024-958Digital Object Identifier
- Title
-
Dynamic Gated Recurrent Neural Network for Compute-efficient Speech EnhancementWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-09-01Full publication date if available
- Authors
-
Longbiao Cheng, Ashutosh Pandey, Buye Xu, Tobi Delbrück, Shih‐Chii LiuList of authors in order
- Landing page
-
https://doi.org/10.21437/interspeech.2024-958Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2408.12425Direct OA link when available
- Concepts
-
Recurrent neural network, Computer science, Inference, Speech enhancement, Reduction (mathematics), Computation, Speech recognition, Speech synthesis, Realization (probability), Artificial intelligence, Artificial neural network, Algorithm, Noise reduction, Mathematics, Statistics, GeometryTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
6Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 6Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4402112230 |
|---|---|
| doi | https://doi.org/10.21437/interspeech.2024-958 |
| ids.doi | https://doi.org/10.21437/interspeech.2024-958 |
| ids.openalex | https://openalex.org/W4402112230 |
| fwci | 4.27502559 |
| type | preprint |
| title | Dynamic Gated Recurrent Neural Network for Compute-efficient Speech Enhancement |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | 681 |
| biblio.first_page | 677 |
| topics[0].id | https://openalex.org/T10860 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9998000264167786 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1711 |
| topics[0].subfield.display_name | Signal Processing |
| topics[0].display_name | Speech and Audio Processing |
| topics[1].id | https://openalex.org/T10201 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9915000200271606 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1702 |
| topics[1].subfield.display_name | Artificial Intelligence |
| topics[1].display_name | Speech Recognition and Synthesis |
| topics[2].id | https://openalex.org/T10326 |
| topics[2].field.id | https://openalex.org/fields/22 |
| topics[2].field.display_name | Engineering |
| topics[2].score | 0.9905999898910522 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/2208 |
| topics[2].subfield.display_name | Electrical and Electronic Engineering |
| topics[2].display_name | Indoor and Outdoor Localization Technologies |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C147168706 |
| concepts[0].level | 3 |
| concepts[0].score | 0.8570429086685181 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q1457734 |
| concepts[0].display_name | Recurrent neural network |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.7731086611747742 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C2776214188 |
| concepts[2].level | 2 |
| concepts[2].score | 0.5606546401977539 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q408386 |
| concepts[2].display_name | Inference |
| concepts[3].id | https://openalex.org/C2776182073 |
| concepts[3].level | 3 |
| concepts[3].score | 0.49761489033699036 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q7575395 |
| concepts[3].display_name | Speech enhancement |
| concepts[4].id | https://openalex.org/C111335779 |
| concepts[4].level | 2 |
| concepts[4].score | 0.4921409487724304 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q3454686 |
| concepts[4].display_name | Reduction (mathematics) |
| concepts[5].id | https://openalex.org/C45374587 |
| concepts[5].level | 2 |
| concepts[5].score | 0.4650263786315918 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q12525525 |
| concepts[5].display_name | Computation |
| concepts[6].id | https://openalex.org/C28490314 |
| concepts[6].level | 1 |
| concepts[6].score | 0.44344061613082886 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q189436 |
| concepts[6].display_name | Speech recognition |
| concepts[7].id | https://openalex.org/C14999030 |
| concepts[7].level | 2 |
| concepts[7].score | 0.4381554424762726 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q16346 |
| concepts[7].display_name | Speech synthesis |
| concepts[8].id | https://openalex.org/C2781089630 |
| concepts[8].level | 2 |
| concepts[8].score | 0.4140395224094391 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q21856745 |
| concepts[8].display_name | Realization (probability) |
| concepts[9].id | https://openalex.org/C154945302 |
| concepts[9].level | 1 |
| concepts[9].score | 0.36388087272644043 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[9].display_name | Artificial intelligence |
| concepts[10].id | https://openalex.org/C50644808 |
| concepts[10].level | 2 |
| concepts[10].score | 0.3416796922683716 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[10].display_name | Artificial neural network |
| concepts[11].id | https://openalex.org/C11413529 |
| concepts[11].level | 1 |
| concepts[11].score | 0.27971550822257996 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q8366 |
| concepts[11].display_name | Algorithm |
| concepts[12].id | https://openalex.org/C163294075 |
| concepts[12].level | 2 |
| concepts[12].score | 0.18923181295394897 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q581861 |
| concepts[12].display_name | Noise reduction |
| concepts[13].id | https://openalex.org/C33923547 |
| concepts[13].level | 0 |
| concepts[13].score | 0.07433399558067322 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[13].display_name | Mathematics |
| concepts[14].id | https://openalex.org/C105795698 |
| concepts[14].level | 1 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q12483 |
| concepts[14].display_name | Statistics |
| concepts[15].id | https://openalex.org/C2524010 |
| concepts[15].level | 1 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q8087 |
| concepts[15].display_name | Geometry |
| keywords[0].id | https://openalex.org/keywords/recurrent-neural-network |
| keywords[0].score | 0.8570429086685181 |
| keywords[0].display_name | Recurrent neural network |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.7731086611747742 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/inference |
| keywords[2].score | 0.5606546401977539 |
| keywords[2].display_name | Inference |
| keywords[3].id | https://openalex.org/keywords/speech-enhancement |
| keywords[3].score | 0.49761489033699036 |
| keywords[3].display_name | Speech enhancement |
| keywords[4].id | https://openalex.org/keywords/reduction |
| keywords[4].score | 0.4921409487724304 |
| keywords[4].display_name | Reduction (mathematics) |
| keywords[5].id | https://openalex.org/keywords/computation |
| keywords[5].score | 0.4650263786315918 |
| keywords[5].display_name | Computation |
| keywords[6].id | https://openalex.org/keywords/speech-recognition |
| keywords[6].score | 0.44344061613082886 |
| keywords[6].display_name | Speech recognition |
| keywords[7].id | https://openalex.org/keywords/speech-synthesis |
| keywords[7].score | 0.4381554424762726 |
| keywords[7].display_name | Speech synthesis |
| keywords[8].id | https://openalex.org/keywords/realization |
| keywords[8].score | 0.4140395224094391 |
| keywords[8].display_name | Realization (probability) |
| keywords[9].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[9].score | 0.36388087272644043 |
| keywords[9].display_name | Artificial intelligence |
| keywords[10].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[10].score | 0.3416796922683716 |
| keywords[10].display_name | Artificial neural network |
| keywords[11].id | https://openalex.org/keywords/algorithm |
| keywords[11].score | 0.27971550822257996 |
| keywords[11].display_name | Algorithm |
| keywords[12].id | https://openalex.org/keywords/noise-reduction |
| keywords[12].score | 0.18923181295394897 |
| keywords[12].display_name | Noise reduction |
| keywords[13].id | https://openalex.org/keywords/mathematics |
| keywords[13].score | 0.07433399558067322 |
| keywords[13].display_name | Mathematics |
| language | en |
| locations[0].id | doi:10.21437/interspeech.2024-958 |
| locations[0].is_oa | False |
| locations[0].source | |
| locations[0].license | |
| locations[0].pdf_url | |
| locations[0].version | publishedVersion |
| locations[0].raw_type | proceedings-article |
| locations[0].license_id | |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Interspeech 2024 |
| locations[0].landing_page_url | https://doi.org/10.21437/interspeech.2024-958 |
| locations[1].id | pmh:oai:arXiv.org:2408.12425 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | |
| locations[1].pdf_url | https://arxiv.org/pdf/2408.12425 |
| locations[1].version | submittedVersion |
| locations[1].raw_type | text |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | False |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | http://arxiv.org/abs/2408.12425 |
| indexed_in | arxiv, crossref |
| authorships[0].author.id | https://openalex.org/A5011611391 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-0635-1480 |
| authorships[0].author.display_name | Longbiao Cheng |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Longbiao Cheng |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5050492887 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-3352-7453 |
| authorships[1].author.display_name | Ashutosh Pandey |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Ashutosh Pandey |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5040562171 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-3027-7567 |
| authorships[2].author.display_name | Buye Xu |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Buye Xu |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5051651857 |
| authorships[3].author.orcid | https://orcid.org/0000-0001-5479-1141 |
| authorships[3].author.display_name | Tobi Delbrück |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Tobi Delbruck |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5053821067 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-7557-045X |
| authorships[4].author.display_name | Shih‐Chii Liu |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Shih-Chii Liu |
| authorships[4].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2408.12425 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Dynamic Gated Recurrent Neural Network for Compute-efficient Speech Enhancement |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T10860 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9998000264167786 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1711 |
| primary_topic.subfield.display_name | Signal Processing |
| primary_topic.display_name | Speech and Audio Processing |
| related_works | https://openalex.org/W4225394202, https://openalex.org/W4298287631, https://openalex.org/W2953061907, https://openalex.org/W2022544890, https://openalex.org/W2394097730, https://openalex.org/W1847088711, https://openalex.org/W3036642985, https://openalex.org/W3032952384, https://openalex.org/W3017902212, https://openalex.org/W2964335273 |
| cited_by_count | 6 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 6 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2408.12425 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2408.12425 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2408.12425 |
| primary_location.id | doi:10.21437/interspeech.2024-958 |
| primary_location.is_oa | False |
| primary_location.source | |
| primary_location.license | |
| primary_location.pdf_url | |
| primary_location.version | publishedVersion |
| primary_location.raw_type | proceedings-article |
| primary_location.license_id | |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Interspeech 2024 |
| primary_location.landing_page_url | https://doi.org/10.21437/interspeech.2024-958 |
| publication_date | 2024-09-01 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 3, 33, 42, 67 |
| abstract_inverted_index.As | 66 |
| abstract_inverted_index.It | 19 |
| abstract_inverted_index.an | 120 |
| abstract_inverted_index.at | 38 |
| abstract_inverted_index.be | 62 |
| abstract_inverted_index.by | 40 |
| abstract_inverted_index.in | 124 |
| abstract_inverted_index.of | 25, 36, 57, 69 |
| abstract_inverted_index.on | 16 |
| abstract_inverted_index.to | 47, 61, 113 |
| abstract_inverted_index.we | 72 |
| abstract_inverted_index.50% | 122 |
| abstract_inverted_index.GRU | 116, 125 |
| abstract_inverted_index.RNN | 49, 60 |
| abstract_inverted_index.and | 30, 109 |
| abstract_inverted_index.new | 4 |
| abstract_inverted_index.not | 82 |
| abstract_inverted_index.set | 35 |
| abstract_inverted_index.the | 21, 48, 54, 58, 70, 96, 101, 114 |
| abstract_inverted_index.Test | 85 |
| abstract_inverted_index.This | 0, 51 |
| abstract_inverted_index.Unit | 78 |
| abstract_inverted_index.cost | 56 |
| abstract_inverted_index.does | 81 |
| abstract_inverted_index.even | 118 |
| abstract_inverted_index.from | 88 |
| abstract_inverted_index.gate | 46 |
| abstract_inverted_index.only | 32 |
| abstract_inverted_index.over | 28 |
| abstract_inverted_index.show | 99 |
| abstract_inverted_index.slow | 22 |
| abstract_inverted_index.that | 100 |
| abstract_inverted_index.with | 119 |
| abstract_inverted_index.D-GRU | 102 |
| abstract_inverted_index.Gated | 6, 76 |
| abstract_inverted_index.based | 103 |
| abstract_inverted_index.model | 104 |
| abstract_inverted_index.newly | 43 |
| abstract_inverted_index.paper | 1 |
| abstract_inverted_index.using | 95 |
| abstract_inverted_index.which | 80 |
| abstract_inverted_index.Neural | 8 |
| abstract_inverted_index.adding | 41 |
| abstract_inverted_index.model. | 50 |
| abstract_inverted_index.models | 14 |
| abstract_inverted_index.select | 45, 52 |
| abstract_inverted_index.speech | 12, 92 |
| abstract_inverted_index.states | 27 |
| abstract_inverted_index.steps, | 29 |
| abstract_inverted_index.(D-GRU) | 79 |
| abstract_inverted_index.DG-RNN, | 71 |
| abstract_inverted_index.Dynamic | 5 |
| abstract_inverted_index.Network | 9 |
| abstract_inverted_index.average | 121 |
| abstract_inverted_index.further | 73 |
| abstract_inverted_index.metrics | 111 |
| abstract_inverted_index.neurons | 37 |
| abstract_inverted_index.propose | 74 |
| abstract_inverted_index.quality | 110 |
| abstract_inverted_index.reduced | 63 |
| abstract_inverted_index.require | 83 |
| abstract_inverted_index.results | 86 |
| abstract_inverted_index.running | 15 |
| abstract_inverted_index.several | 89 |
| abstract_inverted_index.updates | 31 |
| abstract_inverted_index.baseline | 115 |
| abstract_inverted_index.dataset, | 98 |
| abstract_inverted_index.maintain | 106 |
| abstract_inverted_index.obtained | 87 |
| abstract_inverted_index.proposed | 44 |
| abstract_inverted_index.selected | 34 |
| abstract_inverted_index.variants | 105 |
| abstract_inverted_index.RNN-based | 91 |
| abstract_inverted_index.Recurrent | 7, 77 |
| abstract_inverted_index.evolution | 23 |
| abstract_inverted_index.leverages | 20 |
| abstract_inverted_index.reduction | 123 |
| abstract_inverted_index.comparable | 112 |
| abstract_inverted_index.each\nstep | 39 |
| abstract_inverted_index.inference. | 65 |
| abstract_inverted_index.introduces | 2 |
| abstract_inverted_index.platforms. | 18 |
| abstract_inverted_index.RNN\nhidden | 26 |
| abstract_inverted_index.computation | 55 |
| abstract_inverted_index.computes.\n | 126 |
| abstract_inverted_index.enhancement | 13, 93 |
| abstract_inverted_index.realization | 68 |
| abstract_inverted_index.conventional | 59 |
| abstract_inverted_index.gate\nallows | 53 |
| abstract_inverted_index.the\nDynamic | 75 |
| abstract_inverted_index.(DG-RNN)\nfor | 10 |
| abstract_inverted_index.architectures | 94 |
| abstract_inverted_index.based\nmodels | 117 |
| abstract_inverted_index.DNS\nchallenge | 97 |
| abstract_inverted_index.characteristic | 24 |
| abstract_inverted_index.during\nnetwork | 64 |
| abstract_inverted_index.intelligibility | 108 |
| abstract_inverted_index.similar\nspeech | 107 |
| abstract_inverted_index.compute-efficient | 11 |
| abstract_inverted_index.additional\nparameters. | 84 |
| abstract_inverted_index.resource-constrained\nhardware | 17 |
| abstract_inverted_index.state-of-the-art\ncompute-efficient | 90 |
| cited_by_percentile_year.max | 99 |
| cited_by_percentile_year.min | 98 |
| countries_distinct_count | 0 |
| institutions_distinct_count | 5 |
| citation_normalized_percentile.value | 0.92178014 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | True |