Data-Efficient Low-Complexity Acoustic Scene Classification via Distilling and Progressive Pruning Article Swipe
Bing Han
,
Wen Huang
,
Zhengyang Chen
,
Anbai Jiang
,
Pingyi Fan
,
Cheng Lu
,
Zhiqiang Lv
,
Jia Liu
,
Wei-Qiang Zhang
,
Yanmin Qian
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2410.20775
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2410.20775
The goal of the acoustic scene classification (ASC) task is to classify recordings into one of the predefined acoustic scene classes. However, in real-world scenarios, ASC systems often encounter challenges such as recording device mismatch, low-complexity constraints, and the limited availability of labeled data. To alleviate these issues, in this paper, a data-efficient and low-complexity ASC system is built with a new model architecture and better training strategies. Specifically, we firstly design a new low-complexity architecture named Rep-Mobile by integrating multi-convolution branches which can be reparameterized at inference. Compared to other models, it achieves better performance and less computational complexity. Then we apply the knowledge distillation strategy and provide a comparison of the data efficiency of the teacher model with different architectures. Finally, we propose a progressive pruning strategy, which involves pruning the model multiple times in small amounts, resulting in better performance compared to a single step pruning. Experiments are conducted on the TAU dataset. With Rep-Mobile and these training strategies, our proposed ASC system achieves the state-of-the-art (SOTA) results so far, while also winning the first place with a significant advantage over others in the DCASE2024 Challenge.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2410.20775
- https://arxiv.org/pdf/2410.20775
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4404314427
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4404314427Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2410.20775Digital Object Identifier
- Title
-
Data-Efficient Low-Complexity Acoustic Scene Classification via Distilling and Progressive PruningWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-10-28Full publication date if available
- Authors
-
Bing Han, Wen Huang, Zhengyang Chen, Anbai Jiang, Pingyi Fan, Cheng Lu, Zhiqiang Lv, Jia Liu, Wei-Qiang Zhang, Yanmin QianList of authors in order
- Landing page
-
https://arxiv.org/abs/2410.20775Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2410.20775Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2410.20775Direct OA link when available
- Concepts
-
Pruning, Computer science, Artificial intelligence, Pattern recognition (psychology), Machine learning, Horticulture, BiologyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4404314427 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2410.20775 |
| ids.doi | https://doi.org/10.48550/arxiv.2410.20775 |
| ids.openalex | https://openalex.org/W4404314427 |
| fwci | 0.0 |
| type | preprint |
| title | Data-Efficient Low-Complexity Acoustic Scene Classification via Distilling and Progressive Pruning |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| 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 | 0.9976000189781189 |
| 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/T11309 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9962999820709229 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1711 |
| topics[1].subfield.display_name | Signal Processing |
| topics[1].display_name | Music and Audio Processing |
| topics[2].id | https://openalex.org/T10201 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9797000288963318 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1702 |
| topics[2].subfield.display_name | Artificial Intelligence |
| topics[2].display_name | Speech Recognition and Synthesis |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C108010975 |
| concepts[0].level | 2 |
| concepts[0].score | 0.8529738187789917 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q500094 |
| concepts[0].display_name | Pruning |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.5709227323532104 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C154945302 |
| concepts[2].level | 1 |
| concepts[2].score | 0.4863603711128235 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[2].display_name | Artificial intelligence |
| concepts[3].id | https://openalex.org/C153180895 |
| concepts[3].level | 2 |
| concepts[3].score | 0.4223487377166748 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[3].display_name | Pattern recognition (psychology) |
| concepts[4].id | https://openalex.org/C119857082 |
| concepts[4].level | 1 |
| concepts[4].score | 0.3512977957725525 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[4].display_name | Machine learning |
| concepts[5].id | https://openalex.org/C144027150 |
| concepts[5].level | 1 |
| concepts[5].score | 0.07230034470558167 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q48803 |
| concepts[5].display_name | Horticulture |
| concepts[6].id | https://openalex.org/C86803240 |
| concepts[6].level | 0 |
| concepts[6].score | 0.0 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q420 |
| concepts[6].display_name | Biology |
| keywords[0].id | https://openalex.org/keywords/pruning |
| keywords[0].score | 0.8529738187789917 |
| keywords[0].display_name | Pruning |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.5709227323532104 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[2].score | 0.4863603711128235 |
| keywords[2].display_name | Artificial intelligence |
| keywords[3].id | https://openalex.org/keywords/pattern-recognition |
| keywords[3].score | 0.4223487377166748 |
| keywords[3].display_name | Pattern recognition (psychology) |
| keywords[4].id | https://openalex.org/keywords/machine-learning |
| keywords[4].score | 0.3512977957725525 |
| keywords[4].display_name | Machine learning |
| keywords[5].id | https://openalex.org/keywords/horticulture |
| keywords[5].score | 0.07230034470558167 |
| keywords[5].display_name | Horticulture |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2410.20775 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2410.20775 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2410.20775 |
| locations[1].id | doi:10.48550/arxiv.2410.20775 |
| 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 | |
| locations[1].version | |
| locations[1].raw_type | article-journal |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2410.20775 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5100690518 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-6473-0438 |
| authorships[0].author.display_name | Bing Han |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Han, Bing |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5115601911 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-2072-7173 |
| authorships[1].author.display_name | Wen Huang |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Huang, Wen |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5101416769 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-1293-8146 |
| authorships[2].author.display_name | Zhengyang Chen |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Chen, Zhengyang |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5032861798 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Anbai Jiang |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Jiang, Anbai |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5079233004 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-0658-6079 |
| authorships[4].author.display_name | Pingyi Fan |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Fan, Pingyi |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5101476514 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-1062-8550 |
| authorships[5].author.display_name | Cheng Lu |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Lu, Cheng |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5102915022 |
| authorships[6].author.orcid | https://orcid.org/0000-0003-2875-6486 |
| authorships[6].author.display_name | Zhiqiang Lv |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Lv, Zhiqiang |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5115595814 |
| authorships[7].author.orcid | https://orcid.org/0000-0002-9771-192X |
| authorships[7].author.display_name | Jia Liu |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Liu, Jia |
| authorships[7].is_corresponding | False |
| authorships[8].author.id | https://openalex.org/A5100692904 |
| authorships[8].author.orcid | https://orcid.org/0000-0003-3841-1959 |
| authorships[8].author.display_name | Wei-Qiang Zhang |
| authorships[8].author_position | middle |
| authorships[8].raw_author_name | Zhang, Wei-Qiang |
| authorships[8].is_corresponding | False |
| authorships[9].author.id | https://openalex.org/A5100341993 |
| authorships[9].author.orcid | https://orcid.org/0000-0002-0314-3790 |
| authorships[9].author.display_name | Yanmin Qian |
| authorships[9].author_position | last |
| authorships[9].raw_author_name | Qian, Yanmin |
| authorships[9].is_corresponding | False |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2410.20775 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Data-Efficient Low-Complexity Acoustic Scene Classification via Distilling and Progressive Pruning |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| 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 | 0.9976000189781189 |
| 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/W2961085424, https://openalex.org/W4306674287, https://openalex.org/W3046775127, https://openalex.org/W4394896187, https://openalex.org/W3170094116, https://openalex.org/W4386462264, https://openalex.org/W3107602296, https://openalex.org/W4364306694, https://openalex.org/W4312192474, https://openalex.org/W2033914206 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2410.20775 |
| 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/2410.20775 |
| 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/2410.20775 |
| primary_location.id | pmh:oai:arXiv.org:2410.20775 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2410.20775 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2410.20775 |
| publication_date | 2024-10-28 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 51, 60, 72, 109, 125, 145, 180 |
| abstract_inverted_index.To | 44 |
| abstract_inverted_index.as | 31 |
| abstract_inverted_index.at | 86 |
| abstract_inverted_index.be | 84 |
| abstract_inverted_index.by | 78 |
| abstract_inverted_index.in | 22, 48, 136, 140, 185 |
| abstract_inverted_index.is | 9, 57 |
| abstract_inverted_index.it | 92 |
| abstract_inverted_index.of | 2, 15, 41, 111, 115 |
| abstract_inverted_index.on | 152 |
| abstract_inverted_index.so | 171 |
| abstract_inverted_index.to | 10, 89, 144 |
| abstract_inverted_index.we | 69, 101, 123 |
| abstract_inverted_index.ASC | 25, 55, 164 |
| abstract_inverted_index.TAU | 154 |
| abstract_inverted_index.The | 0 |
| abstract_inverted_index.and | 37, 53, 64, 96, 107, 158 |
| abstract_inverted_index.are | 150 |
| abstract_inverted_index.can | 83 |
| abstract_inverted_index.new | 61, 73 |
| abstract_inverted_index.one | 14 |
| abstract_inverted_index.our | 162 |
| abstract_inverted_index.the | 3, 16, 38, 103, 112, 116, 132, 153, 167, 176, 186 |
| abstract_inverted_index.Then | 100 |
| abstract_inverted_index.With | 156 |
| abstract_inverted_index.also | 174 |
| abstract_inverted_index.data | 113 |
| abstract_inverted_index.far, | 172 |
| abstract_inverted_index.goal | 1 |
| abstract_inverted_index.into | 13 |
| abstract_inverted_index.less | 97 |
| abstract_inverted_index.over | 183 |
| abstract_inverted_index.step | 147 |
| abstract_inverted_index.such | 30 |
| abstract_inverted_index.task | 8 |
| abstract_inverted_index.this | 49 |
| abstract_inverted_index.with | 59, 119, 179 |
| abstract_inverted_index.(ASC) | 7 |
| abstract_inverted_index.apply | 102 |
| abstract_inverted_index.built | 58 |
| abstract_inverted_index.data. | 43 |
| abstract_inverted_index.first | 177 |
| abstract_inverted_index.model | 62, 118, 133 |
| abstract_inverted_index.named | 76 |
| abstract_inverted_index.often | 27 |
| abstract_inverted_index.other | 90 |
| abstract_inverted_index.place | 178 |
| abstract_inverted_index.scene | 5, 19 |
| abstract_inverted_index.small | 137 |
| abstract_inverted_index.these | 46, 159 |
| abstract_inverted_index.times | 135 |
| abstract_inverted_index.which | 82, 129 |
| abstract_inverted_index.while | 173 |
| abstract_inverted_index.(SOTA) | 169 |
| abstract_inverted_index.better | 65, 94, 141 |
| abstract_inverted_index.design | 71 |
| abstract_inverted_index.device | 33 |
| abstract_inverted_index.others | 184 |
| abstract_inverted_index.paper, | 50 |
| abstract_inverted_index.single | 146 |
| abstract_inverted_index.system | 56, 165 |
| abstract_inverted_index.firstly | 70 |
| abstract_inverted_index.issues, | 47 |
| abstract_inverted_index.labeled | 42 |
| abstract_inverted_index.limited | 39 |
| abstract_inverted_index.models, | 91 |
| abstract_inverted_index.propose | 124 |
| abstract_inverted_index.provide | 108 |
| abstract_inverted_index.pruning | 127, 131 |
| abstract_inverted_index.results | 170 |
| abstract_inverted_index.systems | 26 |
| abstract_inverted_index.teacher | 117 |
| abstract_inverted_index.winning | 175 |
| abstract_inverted_index.Compared | 88 |
| abstract_inverted_index.Finally, | 122 |
| abstract_inverted_index.However, | 21 |
| abstract_inverted_index.achieves | 93, 166 |
| abstract_inverted_index.acoustic | 4, 18 |
| abstract_inverted_index.amounts, | 138 |
| abstract_inverted_index.branches | 81 |
| abstract_inverted_index.classes. | 20 |
| abstract_inverted_index.classify | 11 |
| abstract_inverted_index.compared | 143 |
| abstract_inverted_index.dataset. | 155 |
| abstract_inverted_index.involves | 130 |
| abstract_inverted_index.multiple | 134 |
| abstract_inverted_index.proposed | 163 |
| abstract_inverted_index.pruning. | 148 |
| abstract_inverted_index.strategy | 106 |
| abstract_inverted_index.training | 66, 160 |
| abstract_inverted_index.DCASE2024 | 187 |
| abstract_inverted_index.advantage | 182 |
| abstract_inverted_index.alleviate | 45 |
| abstract_inverted_index.conducted | 151 |
| abstract_inverted_index.different | 120 |
| abstract_inverted_index.encounter | 28 |
| abstract_inverted_index.knowledge | 104 |
| abstract_inverted_index.mismatch, | 34 |
| abstract_inverted_index.recording | 32 |
| abstract_inverted_index.resulting | 139 |
| abstract_inverted_index.strategy, | 128 |
| abstract_inverted_index.Challenge. | 188 |
| abstract_inverted_index.Rep-Mobile | 77, 157 |
| abstract_inverted_index.challenges | 29 |
| abstract_inverted_index.comparison | 110 |
| abstract_inverted_index.efficiency | 114 |
| abstract_inverted_index.inference. | 87 |
| abstract_inverted_index.predefined | 17 |
| abstract_inverted_index.real-world | 23 |
| abstract_inverted_index.recordings | 12 |
| abstract_inverted_index.scenarios, | 24 |
| abstract_inverted_index.Experiments | 149 |
| abstract_inverted_index.complexity. | 99 |
| abstract_inverted_index.integrating | 79 |
| abstract_inverted_index.performance | 95, 142 |
| abstract_inverted_index.progressive | 126 |
| abstract_inverted_index.significant | 181 |
| abstract_inverted_index.strategies, | 161 |
| abstract_inverted_index.strategies. | 67 |
| abstract_inverted_index.architecture | 63, 75 |
| abstract_inverted_index.availability | 40 |
| abstract_inverted_index.constraints, | 36 |
| abstract_inverted_index.distillation | 105 |
| abstract_inverted_index.Specifically, | 68 |
| abstract_inverted_index.computational | 98 |
| abstract_inverted_index.architectures. | 121 |
| abstract_inverted_index.classification | 6 |
| abstract_inverted_index.data-efficient | 52 |
| abstract_inverted_index.low-complexity | 35, 54, 74 |
| abstract_inverted_index.reparameterized | 85 |
| abstract_inverted_index.state-of-the-art | 168 |
| abstract_inverted_index.multi-convolution | 80 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 10 |
| citation_normalized_percentile.value | 0.27800913 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |