Enhancing Resilience to Missing Data in Audio-Text Emotion Recognition with Multi-Scale Chunk Regularization Article Swipe
Wei-Cheng Lin
,
Lucas Goncalves
,
Carlos Busso
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.1145/3577190.3614110
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.1145/3577190.3614110
Most existing audio-text emotion recognition studies have focused on the computational modeling aspects, including strategies for fusing the modalities. An area that has received less attention is understanding the role of proper temporal synchronization between the modalities in the model performance. This study presents a transformer-based model designed with a word-chunk concept, which offers an ideal framework to explore different strategies to align text and speech. The approach creates chunks with alternative alignment strategies with different levels of dependency on the underlying lexical boundaries. A key contribution of this study is the multi-scale chunk alignment strategy, which generates random alignments to create the chunks without considering lexical boundaries. For every epoch, the approach generates a different alignment for each sentence, serving as an effective regularization method for temporal dependency. Our experimental results based on the MSP-Podcast corpus indicate that providing precise temporal alignment information to create the audio-text chunks does not improve the performance of the system. The attention mechanisms in the transformer-based approach are able to compensate for imperfect synchronization between the modalities. However, using exact lexical boundaries makes the system highly vulnerable to missing modalities. In contrast, the model trained with the proposed multi-scale chunk regularization strategy using random alignment can significantly increase its robustness against missing data and remain effective, even under a single audio-only emotion recognition task. The code is available at: https://github.com/winston-lin-wei-cheng/MultiScale-Chunk-Regularization
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1145/3577190.3614110
- https://dl.acm.org/doi/pdf/10.1145/3577190.3614110
- OA Status
- hybrid
- Cited By
- 5
- References
- 41
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4387421359
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4387421359Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1145/3577190.3614110Digital Object Identifier
- Title
-
Enhancing Resilience to Missing Data in Audio-Text Emotion Recognition with Multi-Scale Chunk RegularizationWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-10-07Full publication date if available
- Authors
-
Wei-Cheng Lin, Lucas Goncalves, Carlos BussoList of authors in order
- Landing page
-
https://doi.org/10.1145/3577190.3614110Publisher landing page
- PDF URL
-
https://dl.acm.org/doi/pdf/10.1145/3577190.3614110Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
hybridOpen access status per OpenAlex
- OA URL
-
https://dl.acm.org/doi/pdf/10.1145/3577190.3614110Direct OA link when available
- Concepts
-
Computer science, Modalities, Hidden Markov model, Speech recognition, Artificial intelligence, Regularization (linguistics), Sentence, Transformer, Natural language processing, Robustness (evolution), Machine learning, Social science, Biochemistry, Quantum mechanics, Sociology, Physics, Chemistry, Gene, VoltageTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
5Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 4, 2024: 1Per-year citation counts (last 5 years)
- References (count)
-
41Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4387421359 |
|---|---|
| doi | https://doi.org/10.1145/3577190.3614110 |
| ids.doi | https://doi.org/10.1145/3577190.3614110 |
| ids.openalex | https://openalex.org/W4387421359 |
| fwci | 0.32648871 |
| type | article |
| title | Enhancing Resilience to Missing Data in Audio-Text Emotion Recognition with Multi-Scale Chunk Regularization |
| awards[0].id | https://openalex.org/G8082180408 |
| awards[0].funder_id | https://openalex.org/F4320306076 |
| awards[0].display_name | |
| awards[0].funder_award_id | CNS-2016719 |
| awards[0].funder_display_name | National Science Foundation |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | 215 |
| biblio.first_page | 207 |
| topics[0].id | https://openalex.org/T11309 |
| 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 | Music and Audio Processing |
| topics[1].id | https://openalex.org/T10860 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9995999932289124 |
| 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 | Speech and Audio Processing |
| topics[2].id | https://openalex.org/T10667 |
| topics[2].field.id | https://openalex.org/fields/32 |
| topics[2].field.display_name | Psychology |
| topics[2].score | 0.9993000030517578 |
| topics[2].domain.id | https://openalex.org/domains/2 |
| topics[2].domain.display_name | Social Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/3205 |
| topics[2].subfield.display_name | Experimental and Cognitive Psychology |
| topics[2].display_name | Emotion and Mood Recognition |
| funders[0].id | https://openalex.org/F4320306076 |
| funders[0].ror | https://ror.org/021nxhr62 |
| funders[0].display_name | National Science Foundation |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.8432561159133911 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C2779903281 |
| concepts[1].level | 2 |
| concepts[1].score | 0.5469326376914978 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q6888026 |
| concepts[1].display_name | Modalities |
| concepts[2].id | https://openalex.org/C23224414 |
| concepts[2].level | 2 |
| concepts[2].score | 0.5331043004989624 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q176769 |
| concepts[2].display_name | Hidden Markov model |
| concepts[3].id | https://openalex.org/C28490314 |
| concepts[3].level | 1 |
| concepts[3].score | 0.5251383781433105 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q189436 |
| concepts[3].display_name | Speech recognition |
| concepts[4].id | https://openalex.org/C154945302 |
| concepts[4].level | 1 |
| concepts[4].score | 0.49808573722839355 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[4].display_name | Artificial intelligence |
| concepts[5].id | https://openalex.org/C2776135515 |
| concepts[5].level | 2 |
| concepts[5].score | 0.48535671830177307 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q17143721 |
| concepts[5].display_name | Regularization (linguistics) |
| concepts[6].id | https://openalex.org/C2777530160 |
| concepts[6].level | 2 |
| concepts[6].score | 0.43545016646385193 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q41796 |
| concepts[6].display_name | Sentence |
| concepts[7].id | https://openalex.org/C66322947 |
| concepts[7].level | 3 |
| concepts[7].score | 0.4340859651565552 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q11658 |
| concepts[7].display_name | Transformer |
| concepts[8].id | https://openalex.org/C204321447 |
| concepts[8].level | 1 |
| concepts[8].score | 0.42429620027542114 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[8].display_name | Natural language processing |
| concepts[9].id | https://openalex.org/C63479239 |
| concepts[9].level | 3 |
| concepts[9].score | 0.4115551710128784 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q7353546 |
| concepts[9].display_name | Robustness (evolution) |
| concepts[10].id | https://openalex.org/C119857082 |
| concepts[10].level | 1 |
| concepts[10].score | 0.33980751037597656 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[10].display_name | Machine learning |
| concepts[11].id | https://openalex.org/C36289849 |
| concepts[11].level | 1 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q34749 |
| concepts[11].display_name | Social science |
| concepts[12].id | https://openalex.org/C55493867 |
| concepts[12].level | 1 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q7094 |
| concepts[12].display_name | Biochemistry |
| concepts[13].id | https://openalex.org/C62520636 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q944 |
| concepts[13].display_name | Quantum mechanics |
| concepts[14].id | https://openalex.org/C144024400 |
| concepts[14].level | 0 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q21201 |
| concepts[14].display_name | Sociology |
| concepts[15].id | https://openalex.org/C121332964 |
| concepts[15].level | 0 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[15].display_name | Physics |
| concepts[16].id | https://openalex.org/C185592680 |
| concepts[16].level | 0 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q2329 |
| concepts[16].display_name | Chemistry |
| concepts[17].id | https://openalex.org/C104317684 |
| concepts[17].level | 2 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q7187 |
| concepts[17].display_name | Gene |
| concepts[18].id | https://openalex.org/C165801399 |
| concepts[18].level | 2 |
| concepts[18].score | 0.0 |
| concepts[18].wikidata | https://www.wikidata.org/wiki/Q25428 |
| concepts[18].display_name | Voltage |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.8432561159133911 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/modalities |
| keywords[1].score | 0.5469326376914978 |
| keywords[1].display_name | Modalities |
| keywords[2].id | https://openalex.org/keywords/hidden-markov-model |
| keywords[2].score | 0.5331043004989624 |
| keywords[2].display_name | Hidden Markov model |
| keywords[3].id | https://openalex.org/keywords/speech-recognition |
| keywords[3].score | 0.5251383781433105 |
| keywords[3].display_name | Speech recognition |
| keywords[4].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[4].score | 0.49808573722839355 |
| keywords[4].display_name | Artificial intelligence |
| keywords[5].id | https://openalex.org/keywords/regularization |
| keywords[5].score | 0.48535671830177307 |
| keywords[5].display_name | Regularization (linguistics) |
| keywords[6].id | https://openalex.org/keywords/sentence |
| keywords[6].score | 0.43545016646385193 |
| keywords[6].display_name | Sentence |
| keywords[7].id | https://openalex.org/keywords/transformer |
| keywords[7].score | 0.4340859651565552 |
| keywords[7].display_name | Transformer |
| keywords[8].id | https://openalex.org/keywords/natural-language-processing |
| keywords[8].score | 0.42429620027542114 |
| keywords[8].display_name | Natural language processing |
| keywords[9].id | https://openalex.org/keywords/robustness |
| keywords[9].score | 0.4115551710128784 |
| keywords[9].display_name | Robustness (evolution) |
| keywords[10].id | https://openalex.org/keywords/machine-learning |
| keywords[10].score | 0.33980751037597656 |
| keywords[10].display_name | Machine learning |
| language | en |
| locations[0].id | doi:10.1145/3577190.3614110 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4363608440 |
| locations[0].source.issn | |
| locations[0].source.type | conference |
| locations[0].source.is_oa | False |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION |
| locations[0].source.host_organization | |
| locations[0].source.host_organization_name | |
| locations[0].license | cc-by-nc-nd |
| locations[0].pdf_url | https://dl.acm.org/doi/pdf/10.1145/3577190.3614110 |
| locations[0].version | publishedVersion |
| locations[0].raw_type | proceedings-article |
| locations[0].license_id | https://openalex.org/licenses/cc-by-nc-nd |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION |
| locations[0].landing_page_url | https://doi.org/10.1145/3577190.3614110 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5070819601 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-1933-1590 |
| authorships[0].author.display_name | Wei-Cheng Lin |
| authorships[0].countries | US |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I162577319 |
| authorships[0].affiliations[0].raw_affiliation_string | Electrical and Computer Engineering, The University of Texas at Dallas, United States |
| authorships[0].institutions[0].id | https://openalex.org/I162577319 |
| authorships[0].institutions[0].ror | https://ror.org/049emcs32 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I162577319 |
| authorships[0].institutions[0].country_code | US |
| authorships[0].institutions[0].display_name | The University of Texas at Dallas |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Wei-Cheng Lin |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Electrical and Computer Engineering, The University of Texas at Dallas, United States |
| authorships[1].author.id | https://openalex.org/A5017966455 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-9613-1002 |
| authorships[1].author.display_name | Lucas Goncalves |
| authorships[1].countries | US |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I162577319 |
| authorships[1].affiliations[0].raw_affiliation_string | Electrical and Computer Engineering, The University of Texas at Dallas, United States |
| authorships[1].institutions[0].id | https://openalex.org/I162577319 |
| authorships[1].institutions[0].ror | https://ror.org/049emcs32 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I162577319 |
| authorships[1].institutions[0].country_code | US |
| authorships[1].institutions[0].display_name | The University of Texas at Dallas |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Lucas Goncalves |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Electrical and Computer Engineering, The University of Texas at Dallas, United States |
| authorships[2].author.id | https://openalex.org/A5040793194 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-4075-4072 |
| authorships[2].author.display_name | Carlos Busso |
| authorships[2].countries | US |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I162577319 |
| authorships[2].affiliations[0].raw_affiliation_string | Electrical and Computer Engineering, The University of Texas at Dallas, United States |
| authorships[2].institutions[0].id | https://openalex.org/I162577319 |
| authorships[2].institutions[0].ror | https://ror.org/049emcs32 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I162577319 |
| authorships[2].institutions[0].country_code | US |
| authorships[2].institutions[0].display_name | The University of Texas at Dallas |
| authorships[2].author_position | last |
| authorships[2].raw_author_name | Carlos Busso |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | Electrical and Computer Engineering, The University of Texas at Dallas, United States |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://dl.acm.org/doi/pdf/10.1145/3577190.3614110 |
| open_access.oa_status | hybrid |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Enhancing Resilience to Missing Data in Audio-Text Emotion Recognition with Multi-Scale Chunk Regularization |
| has_fulltext | True |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T11309 |
| 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 | Music and Audio Processing |
| related_works | https://openalex.org/W2053269318, https://openalex.org/W2364370872, https://openalex.org/W2185469136, https://openalex.org/W2025614924, https://openalex.org/W2294335174, https://openalex.org/W2097963413, https://openalex.org/W3145575561, https://openalex.org/W2001275470, https://openalex.org/W2073996508, https://openalex.org/W4281476908 |
| cited_by_count | 5 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 4 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 1 |
| locations_count | 1 |
| best_oa_location.id | doi:10.1145/3577190.3614110 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4363608440 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | conference |
| best_oa_location.source.is_oa | False |
| 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 | INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION |
| best_oa_location.source.host_organization | |
| best_oa_location.source.host_organization_name | |
| best_oa_location.license | cc-by-nc-nd |
| best_oa_location.pdf_url | https://dl.acm.org/doi/pdf/10.1145/3577190.3614110 |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | proceedings-article |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by-nc-nd |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION |
| best_oa_location.landing_page_url | https://doi.org/10.1145/3577190.3614110 |
| primary_location.id | doi:10.1145/3577190.3614110 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4363608440 |
| primary_location.source.issn | |
| primary_location.source.type | conference |
| primary_location.source.is_oa | False |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION |
| primary_location.source.host_organization | |
| primary_location.source.host_organization_name | |
| primary_location.license | cc-by-nc-nd |
| primary_location.pdf_url | https://dl.acm.org/doi/pdf/10.1145/3577190.3614110 |
| primary_location.version | publishedVersion |
| primary_location.raw_type | proceedings-article |
| primary_location.license_id | https://openalex.org/licenses/cc-by-nc-nd |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION |
| primary_location.landing_page_url | https://doi.org/10.1145/3577190.3614110 |
| publication_date | 2023-10-07 |
| publication_year | 2023 |
| referenced_works | https://openalex.org/W2619383789, https://openalex.org/W2525412388, https://openalex.org/W2143350951, https://openalex.org/W2117752179, https://openalex.org/W3207579445, https://openalex.org/W1985867508, https://openalex.org/W2887761937, https://openalex.org/W4312976151, https://openalex.org/W4376632472, https://openalex.org/W2109255472, https://openalex.org/W3184369217, https://openalex.org/W1981395202, https://openalex.org/W2997026866, https://openalex.org/W1992475611, https://openalex.org/W3095118468, https://openalex.org/W3164582967, https://openalex.org/W2965373594, https://openalex.org/W2742542661, https://openalex.org/W2401417847, https://openalex.org/W1970155934, https://openalex.org/W2747874407, https://openalex.org/W2997258743, https://openalex.org/W4287777846, https://openalex.org/W3114214226, https://openalex.org/W2962931510, https://openalex.org/W4309799497, https://openalex.org/W3088631780, https://openalex.org/W2164699598, https://openalex.org/W2787247660, https://openalex.org/W2972852081, https://openalex.org/W2964051877, https://openalex.org/W2068124150, https://openalex.org/W4361994820, https://openalex.org/W3198220993, https://openalex.org/W2980282514, https://openalex.org/W3014163061, https://openalex.org/W2897337310, https://openalex.org/W6922016914, https://openalex.org/W2619941915, https://openalex.org/W2730845691, https://openalex.org/W2592549418 |
| referenced_works_count | 41 |
| abstract_inverted_index.A | 84 |
| abstract_inverted_index.a | 44, 49, 114, 215 |
| abstract_inverted_index.An | 19 |
| abstract_inverted_index.In | 187 |
| abstract_inverted_index.an | 54, 122 |
| abstract_inverted_index.as | 121 |
| abstract_inverted_index.in | 37, 160 |
| abstract_inverted_index.is | 26, 90, 223 |
| abstract_inverted_index.of | 30, 77, 87, 154 |
| abstract_inverted_index.on | 8, 79, 133 |
| abstract_inverted_index.to | 57, 61, 100, 144, 166, 184 |
| abstract_inverted_index.For | 108 |
| abstract_inverted_index.Our | 129 |
| abstract_inverted_index.The | 66, 157, 221 |
| abstract_inverted_index.and | 64, 210 |
| abstract_inverted_index.are | 164 |
| abstract_inverted_index.at: | 225 |
| abstract_inverted_index.can | 202 |
| abstract_inverted_index.for | 15, 117, 126, 168 |
| abstract_inverted_index.has | 22 |
| abstract_inverted_index.its | 205 |
| abstract_inverted_index.key | 85 |
| abstract_inverted_index.not | 150 |
| abstract_inverted_index.the | 9, 17, 28, 35, 38, 80, 91, 102, 111, 134, 146, 152, 155, 161, 172, 180, 189, 193 |
| abstract_inverted_index.Most | 0 |
| abstract_inverted_index.This | 41 |
| abstract_inverted_index.able | 165 |
| abstract_inverted_index.area | 20 |
| abstract_inverted_index.code | 222 |
| abstract_inverted_index.data | 209 |
| abstract_inverted_index.does | 149 |
| abstract_inverted_index.each | 118 |
| abstract_inverted_index.even | 213 |
| abstract_inverted_index.have | 6 |
| abstract_inverted_index.less | 24 |
| abstract_inverted_index.role | 29 |
| abstract_inverted_index.text | 63 |
| abstract_inverted_index.that | 21, 138 |
| abstract_inverted_index.this | 88 |
| abstract_inverted_index.with | 48, 70, 74, 192 |
| abstract_inverted_index.align | 62 |
| abstract_inverted_index.based | 132 |
| abstract_inverted_index.chunk | 93, 196 |
| abstract_inverted_index.every | 109 |
| abstract_inverted_index.exact | 176 |
| abstract_inverted_index.ideal | 55 |
| abstract_inverted_index.makes | 179 |
| abstract_inverted_index.model | 39, 46, 190 |
| abstract_inverted_index.study | 42, 89 |
| abstract_inverted_index.task. | 220 |
| abstract_inverted_index.under | 214 |
| abstract_inverted_index.using | 175, 199 |
| abstract_inverted_index.which | 52, 96 |
| abstract_inverted_index.chunks | 69, 103, 148 |
| abstract_inverted_index.corpus | 136 |
| abstract_inverted_index.create | 101, 145 |
| abstract_inverted_index.epoch, | 110 |
| abstract_inverted_index.fusing | 16 |
| abstract_inverted_index.highly | 182 |
| abstract_inverted_index.levels | 76 |
| abstract_inverted_index.method | 125 |
| abstract_inverted_index.offers | 53 |
| abstract_inverted_index.proper | 31 |
| abstract_inverted_index.random | 98, 200 |
| abstract_inverted_index.remain | 211 |
| abstract_inverted_index.single | 216 |
| abstract_inverted_index.system | 181 |
| abstract_inverted_index.against | 207 |
| abstract_inverted_index.between | 34, 171 |
| abstract_inverted_index.creates | 68 |
| abstract_inverted_index.emotion | 3, 218 |
| abstract_inverted_index.explore | 58 |
| abstract_inverted_index.focused | 7 |
| abstract_inverted_index.improve | 151 |
| abstract_inverted_index.lexical | 82, 106, 177 |
| abstract_inverted_index.missing | 185, 208 |
| abstract_inverted_index.precise | 140 |
| abstract_inverted_index.results | 131 |
| abstract_inverted_index.serving | 120 |
| abstract_inverted_index.speech. | 65 |
| abstract_inverted_index.studies | 5 |
| abstract_inverted_index.system. | 156 |
| abstract_inverted_index.trained | 191 |
| abstract_inverted_index.without | 104 |
| abstract_inverted_index.However, | 174 |
| abstract_inverted_index.approach | 67, 112, 163 |
| abstract_inverted_index.aspects, | 12 |
| abstract_inverted_index.concept, | 51 |
| abstract_inverted_index.designed | 47 |
| abstract_inverted_index.existing | 1 |
| abstract_inverted_index.increase | 204 |
| abstract_inverted_index.indicate | 137 |
| abstract_inverted_index.modeling | 11 |
| abstract_inverted_index.presents | 43 |
| abstract_inverted_index.proposed | 194 |
| abstract_inverted_index.received | 23 |
| abstract_inverted_index.strategy | 198 |
| abstract_inverted_index.temporal | 32, 127, 141 |
| abstract_inverted_index.alignment | 72, 94, 116, 142, 201 |
| abstract_inverted_index.attention | 25, 158 |
| abstract_inverted_index.available | 224 |
| abstract_inverted_index.contrast, | 188 |
| abstract_inverted_index.different | 59, 75, 115 |
| abstract_inverted_index.effective | 123 |
| abstract_inverted_index.framework | 56 |
| abstract_inverted_index.generates | 97, 113 |
| abstract_inverted_index.imperfect | 169 |
| abstract_inverted_index.including | 13 |
| abstract_inverted_index.providing | 139 |
| abstract_inverted_index.sentence, | 119 |
| abstract_inverted_index.strategy, | 95 |
| abstract_inverted_index.alignments | 99 |
| abstract_inverted_index.audio-only | 217 |
| abstract_inverted_index.audio-text | 2, 147 |
| abstract_inverted_index.boundaries | 178 |
| abstract_inverted_index.compensate | 167 |
| abstract_inverted_index.dependency | 78 |
| abstract_inverted_index.effective, | 212 |
| abstract_inverted_index.mechanisms | 159 |
| abstract_inverted_index.modalities | 36 |
| abstract_inverted_index.robustness | 206 |
| abstract_inverted_index.strategies | 14, 60, 73 |
| abstract_inverted_index.underlying | 81 |
| abstract_inverted_index.vulnerable | 183 |
| abstract_inverted_index.word-chunk | 50 |
| abstract_inverted_index.MSP-Podcast | 135 |
| abstract_inverted_index.alternative | 71 |
| abstract_inverted_index.boundaries. | 83, 107 |
| abstract_inverted_index.considering | 105 |
| abstract_inverted_index.dependency. | 128 |
| abstract_inverted_index.information | 143 |
| abstract_inverted_index.modalities. | 18, 173, 186 |
| abstract_inverted_index.multi-scale | 92, 195 |
| abstract_inverted_index.performance | 153 |
| abstract_inverted_index.recognition | 4, 219 |
| abstract_inverted_index.contribution | 86 |
| abstract_inverted_index.experimental | 130 |
| abstract_inverted_index.performance. | 40 |
| abstract_inverted_index.computational | 10 |
| abstract_inverted_index.significantly | 203 |
| abstract_inverted_index.understanding | 27 |
| abstract_inverted_index.regularization | 124, 197 |
| abstract_inverted_index.synchronization | 33, 170 |
| abstract_inverted_index.transformer-based | 45, 162 |
| abstract_inverted_index.https://github.com/winston-lin-wei-cheng/MultiScale-Chunk-Regularization | 226 |
| cited_by_percentile_year.max | 98 |
| cited_by_percentile_year.min | 90 |
| countries_distinct_count | 1 |
| institutions_distinct_count | 3 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/16 |
| sustainable_development_goals[0].score | 0.5099999904632568 |
| sustainable_development_goals[0].display_name | Peace, Justice and strong institutions |
| citation_normalized_percentile.value | 0.675 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |