An Improvement to Conformer-Based Model for High-Accuracy Speech Feature Extraction and Learning Article Swipe
Owing to the loss of effective information and incomplete feature extraction caused by the convolution and pooling operations in a convolution subsampling network, the accuracy and speed of current speech processing architectures based on the conformer model are influenced because the shallow features of speech signals are not completely extracted. To solve these problems, in this study, we researched a method that used a capsule network to improve the accuracy of feature extraction in a conformer-based model, and then, we proposed a new end-to-end model architecture for speech recognition. First, to improve the accuracy of speech feature extraction, a capsule network with a dynamic routing mechanism was introduced into the conformer model; thus, the structural information in speech was preserved, and it was input to the conformer blocks via sequestered vectors; the learning ability of the conformed-based model was significantly enhanced using dynamic weight updating. Second, a residual network was added to the capsule blocks, thus, the mapping ability of our model was improved and the training difficulty was reduced. Furthermore, the bi-transformer model was adopted in the decoding network to promote the consistency of the hypotheses in different directions through bidirectional modeling. Finally, the effectiveness and robustness of the proposed model were verified against different types of recognition models by performing multiple sets of experiments. The experimental results demonstrated that our speech recognition model achieved a lower word error rate without a language model because of the higher accuracy of speech feature extraction and learning using our model architecture with a capsule network. Furthermore, our model architecture benefited from the advantage of the capsule network and the conformer encoder, and also has potential for other speech-related applications.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.3390/e24070866
- https://www.mdpi.com/1099-4300/24/7/866/pdf?version=1657090549
- OA Status
- gold
- Cited By
- 5
- References
- 30
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4283364647
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4283364647Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.3390/e24070866Digital Object Identifier
- Title
-
An Improvement to Conformer-Based Model for High-Accuracy Speech Feature Extraction and LearningWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2022Year of publication
- Publication date
-
2022-06-23Full publication date if available
- Authors
-
Mengzhuo Liu, Yangjie WeiList of authors in order
- Landing page
-
https://doi.org/10.3390/e24070866Publisher landing page
- PDF URL
-
https://www.mdpi.com/1099-4300/24/7/866/pdf?version=1657090549Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
goldOpen access status per OpenAlex
- OA URL
-
https://www.mdpi.com/1099-4300/24/7/866/pdf?version=1657090549Direct OA link when available
- Concepts
-
Computer science, Robustness (evolution), Feature extraction, Speech recognition, Artificial intelligence, Pattern recognition (psychology), Chemistry, Biochemistry, GeneTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
5Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 1, 2024: 3, 2023: 1Per-year citation counts (last 5 years)
- References (count)
-
30Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4283364647 |
|---|---|
| doi | https://doi.org/10.3390/e24070866 |
| ids.doi | https://doi.org/10.3390/e24070866 |
| ids.pmid | https://pubmed.ncbi.nlm.nih.gov/35885089 |
| ids.openalex | https://openalex.org/W4283364647 |
| fwci | 0.9789941 |
| type | article |
| title | An Improvement to Conformer-Based Model for High-Accuracy Speech Feature Extraction and Learning |
| awards[0].id | https://openalex.org/G5286270674 |
| awards[0].funder_id | https://openalex.org/F4320321001 |
| awards[0].display_name | |
| awards[0].funder_award_id | 61973059 |
| awards[0].funder_display_name | National Natural Science Foundation of China |
| biblio.issue | 7 |
| biblio.volume | 24 |
| biblio.last_page | 866 |
| biblio.first_page | 866 |
| topics[0].id | https://openalex.org/T10201 |
| 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/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Speech Recognition and Synthesis |
| 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 | 0.9986000061035156 |
| 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/T10860 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9976000189781189 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1711 |
| topics[2].subfield.display_name | Signal Processing |
| topics[2].display_name | Speech and Audio Processing |
| funders[0].id | https://openalex.org/F4320321001 |
| funders[0].ror | https://ror.org/01h0zpd94 |
| funders[0].display_name | National Natural Science Foundation of China |
| is_xpac | False |
| apc_list.value | 2000 |
| apc_list.currency | CHF |
| apc_list.value_usd | 2165 |
| apc_paid.value | 2000 |
| apc_paid.currency | CHF |
| apc_paid.value_usd | 2165 |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.7854329943656921 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C63479239 |
| concepts[1].level | 3 |
| concepts[1].score | 0.6511724591255188 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q7353546 |
| concepts[1].display_name | Robustness (evolution) |
| concepts[2].id | https://openalex.org/C52622490 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6003574728965759 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q1026626 |
| concepts[2].display_name | Feature extraction |
| concepts[3].id | https://openalex.org/C28490314 |
| concepts[3].level | 1 |
| concepts[3].score | 0.505254328250885 |
| 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 | 0.49735167622566223 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[4].display_name | Artificial intelligence |
| concepts[5].id | https://openalex.org/C153180895 |
| concepts[5].level | 2 |
| concepts[5].score | 0.47815975546836853 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[5].display_name | Pattern recognition (psychology) |
| concepts[6].id | https://openalex.org/C185592680 |
| concepts[6].level | 0 |
| concepts[6].score | 0.0 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q2329 |
| concepts[6].display_name | Chemistry |
| concepts[7].id | https://openalex.org/C55493867 |
| concepts[7].level | 1 |
| concepts[7].score | 0.0 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q7094 |
| concepts[7].display_name | Biochemistry |
| concepts[8].id | https://openalex.org/C104317684 |
| concepts[8].level | 2 |
| concepts[8].score | 0.0 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q7187 |
| concepts[8].display_name | Gene |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.7854329943656921 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/robustness |
| keywords[1].score | 0.6511724591255188 |
| keywords[1].display_name | Robustness (evolution) |
| keywords[2].id | https://openalex.org/keywords/feature-extraction |
| keywords[2].score | 0.6003574728965759 |
| keywords[2].display_name | Feature extraction |
| keywords[3].id | https://openalex.org/keywords/speech-recognition |
| keywords[3].score | 0.505254328250885 |
| keywords[3].display_name | Speech recognition |
| keywords[4].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[4].score | 0.49735167622566223 |
| keywords[4].display_name | Artificial intelligence |
| keywords[5].id | https://openalex.org/keywords/pattern-recognition |
| keywords[5].score | 0.47815975546836853 |
| keywords[5].display_name | Pattern recognition (psychology) |
| language | en |
| locations[0].id | doi:10.3390/e24070866 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S195231649 |
| locations[0].source.issn | 1099-4300 |
| locations[0].source.type | journal |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | 1099-4300 |
| locations[0].source.is_core | True |
| locations[0].source.is_in_doaj | True |
| locations[0].source.display_name | Entropy |
| locations[0].source.host_organization | https://openalex.org/P4310310987 |
| locations[0].source.host_organization_name | Multidisciplinary Digital Publishing Institute |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310310987 |
| locations[0].source.host_organization_lineage_names | Multidisciplinary Digital Publishing Institute |
| locations[0].license | cc-by |
| locations[0].pdf_url | https://www.mdpi.com/1099-4300/24/7/866/pdf?version=1657090549 |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Entropy |
| locations[0].landing_page_url | https://doi.org/10.3390/e24070866 |
| locations[1].id | pmid:35885089 |
| locations[1].is_oa | False |
| locations[1].source.id | https://openalex.org/S4306525036 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | False |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | PubMed |
| locations[1].source.host_organization | https://openalex.org/I1299303238 |
| locations[1].source.host_organization_name | National Institutes of Health |
| locations[1].source.host_organization_lineage | https://openalex.org/I1299303238 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | publishedVersion |
| locations[1].raw_type | |
| locations[1].license_id | |
| locations[1].is_accepted | True |
| locations[1].is_published | True |
| locations[1].raw_source_name | Entropy (Basel, Switzerland) |
| locations[1].landing_page_url | https://pubmed.ncbi.nlm.nih.gov/35885089 |
| locations[2].id | pmh:oai:doaj.org/article:70f79105a930439abd0debd4a2d671ce |
| locations[2].is_oa | True |
| locations[2].source.id | https://openalex.org/S4306401280 |
| locations[2].source.issn | |
| locations[2].source.type | repository |
| locations[2].source.is_oa | False |
| locations[2].source.issn_l | |
| locations[2].source.is_core | False |
| locations[2].source.is_in_doaj | False |
| locations[2].source.display_name | DOAJ (DOAJ: Directory of Open Access Journals) |
| locations[2].source.host_organization | |
| locations[2].source.host_organization_name | |
| locations[2].license | cc-by-sa |
| locations[2].pdf_url | |
| locations[2].version | submittedVersion |
| locations[2].raw_type | article |
| locations[2].license_id | https://openalex.org/licenses/cc-by-sa |
| locations[2].is_accepted | False |
| locations[2].is_published | False |
| locations[2].raw_source_name | Entropy, Vol 24, Iss 7, p 866 (2022) |
| locations[2].landing_page_url | https://doaj.org/article/70f79105a930439abd0debd4a2d671ce |
| locations[3].id | pmh:oai:mdpi.com:/1099-4300/24/7/866/ |
| locations[3].is_oa | True |
| locations[3].source.id | https://openalex.org/S4306400947 |
| locations[3].source.issn | |
| locations[3].source.type | repository |
| locations[3].source.is_oa | True |
| locations[3].source.issn_l | |
| locations[3].source.is_core | False |
| locations[3].source.is_in_doaj | False |
| locations[3].source.display_name | MDPI (MDPI AG) |
| locations[3].source.host_organization | https://openalex.org/I4210097602 |
| locations[3].source.host_organization_name | Multidisciplinary Digital Publishing Institute (Switzerland) |
| locations[3].source.host_organization_lineage | https://openalex.org/I4210097602 |
| locations[3].license | cc-by |
| locations[3].pdf_url | |
| locations[3].version | submittedVersion |
| locations[3].raw_type | Text |
| locations[3].license_id | https://openalex.org/licenses/cc-by |
| locations[3].is_accepted | False |
| locations[3].is_published | False |
| locations[3].raw_source_name | Entropy; Volume 24; Issue 7; Pages: 866 |
| locations[3].landing_page_url | https://dx.doi.org/10.3390/e24070866 |
| locations[4].id | pmh:oai:pubmedcentral.nih.gov:9324068 |
| locations[4].is_oa | True |
| locations[4].source.id | https://openalex.org/S2764455111 |
| locations[4].source.issn | |
| locations[4].source.type | repository |
| locations[4].source.is_oa | False |
| locations[4].source.issn_l | |
| locations[4].source.is_core | False |
| locations[4].source.is_in_doaj | False |
| locations[4].source.display_name | PubMed Central |
| locations[4].source.host_organization | https://openalex.org/I1299303238 |
| locations[4].source.host_organization_name | National Institutes of Health |
| locations[4].source.host_organization_lineage | https://openalex.org/I1299303238 |
| locations[4].license | other-oa |
| locations[4].pdf_url | |
| locations[4].version | submittedVersion |
| locations[4].raw_type | Text |
| locations[4].license_id | https://openalex.org/licenses/other-oa |
| locations[4].is_accepted | False |
| locations[4].is_published | False |
| locations[4].raw_source_name | Entropy (Basel) |
| locations[4].landing_page_url | https://www.ncbi.nlm.nih.gov/pmc/articles/9324068 |
| indexed_in | crossref, doaj, pubmed |
| authorships[0].author.id | https://openalex.org/A5035998401 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Mengzhuo Liu |
| authorships[0].countries | CN |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I9224756 |
| authorships[0].affiliations[0].raw_affiliation_string | College of Computer Science and Engineering, Northeastern University, Wenhua Street 3, Shenyang 110819, China |
| authorships[0].institutions[0].id | https://openalex.org/I9224756 |
| authorships[0].institutions[0].ror | https://ror.org/03awzbc87 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I9224756 |
| authorships[0].institutions[0].country_code | CN |
| authorships[0].institutions[0].display_name | Northeastern University |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Mengzhuo Liu |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | College of Computer Science and Engineering, Northeastern University, Wenhua Street 3, Shenyang 110819, China |
| authorships[1].author.id | https://openalex.org/A5025048527 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-6615-5484 |
| authorships[1].author.display_name | Yangjie Wei |
| authorships[1].countries | CN |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I9224756 |
| authorships[1].affiliations[0].raw_affiliation_string | College of Computer Science and Engineering, Northeastern University, Wenhua Street 3, Shenyang 110819, China |
| authorships[1].institutions[0].id | https://openalex.org/I9224756 |
| authorships[1].institutions[0].ror | https://ror.org/03awzbc87 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I9224756 |
| authorships[1].institutions[0].country_code | CN |
| authorships[1].institutions[0].display_name | Northeastern University |
| authorships[1].author_position | last |
| authorships[1].raw_author_name | Yangjie Wei |
| authorships[1].is_corresponding | True |
| authorships[1].raw_affiliation_strings | College of Computer Science and Engineering, Northeastern University, Wenhua Street 3, Shenyang 110819, China |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://www.mdpi.com/1099-4300/24/7/866/pdf?version=1657090549 |
| open_access.oa_status | gold |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | An Improvement to Conformer-Based Model for High-Accuracy Speech Feature Extraction and Learning |
| has_fulltext | True |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T10201 |
| 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/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Speech Recognition and Synthesis |
| related_works | https://openalex.org/W2033914206, https://openalex.org/W1996690921, https://openalex.org/W2042327336, https://openalex.org/W2601157893, https://openalex.org/W2373006798, https://openalex.org/W2131735617, https://openalex.org/W2056912418, https://openalex.org/W2033213769, https://openalex.org/W4312376745, https://openalex.org/W2136016640 |
| cited_by_count | 5 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 1 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 3 |
| counts_by_year[2].year | 2023 |
| counts_by_year[2].cited_by_count | 1 |
| locations_count | 5 |
| best_oa_location.id | doi:10.3390/e24070866 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S195231649 |
| best_oa_location.source.issn | 1099-4300 |
| best_oa_location.source.type | journal |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | 1099-4300 |
| best_oa_location.source.is_core | True |
| best_oa_location.source.is_in_doaj | True |
| best_oa_location.source.display_name | Entropy |
| best_oa_location.source.host_organization | https://openalex.org/P4310310987 |
| best_oa_location.source.host_organization_name | Multidisciplinary Digital Publishing Institute |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4310310987 |
| best_oa_location.source.host_organization_lineage_names | Multidisciplinary Digital Publishing Institute |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | https://www.mdpi.com/1099-4300/24/7/866/pdf?version=1657090549 |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-article |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | Entropy |
| best_oa_location.landing_page_url | https://doi.org/10.3390/e24070866 |
| primary_location.id | doi:10.3390/e24070866 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S195231649 |
| primary_location.source.issn | 1099-4300 |
| primary_location.source.type | journal |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | 1099-4300 |
| primary_location.source.is_core | True |
| primary_location.source.is_in_doaj | True |
| primary_location.source.display_name | Entropy |
| primary_location.source.host_organization | https://openalex.org/P4310310987 |
| primary_location.source.host_organization_name | Multidisciplinary Digital Publishing Institute |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310310987 |
| primary_location.source.host_organization_lineage_names | Multidisciplinary Digital Publishing Institute |
| primary_location.license | cc-by |
| primary_location.pdf_url | https://www.mdpi.com/1099-4300/24/7/866/pdf?version=1657090549 |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Entropy |
| primary_location.landing_page_url | https://doi.org/10.3390/e24070866 |
| publication_date | 2022-06-23 |
| publication_year | 2022 |
| referenced_works | https://openalex.org/W3136499730, https://openalex.org/W2952218014, https://openalex.org/W2327501763, https://openalex.org/W2966272068, https://openalex.org/W2587088898, https://openalex.org/W1995562189, https://openalex.org/W2147768505, https://openalex.org/W2618530766, https://openalex.org/W2963882470, https://openalex.org/W4280563486, https://openalex.org/W2936113082, https://openalex.org/W2097117768, https://openalex.org/W6739901393, https://openalex.org/W6774054309, https://openalex.org/W2948981900, https://openalex.org/W2972818416, https://openalex.org/W3097777922, https://openalex.org/W3016219267, https://openalex.org/W2936774411, https://openalex.org/W2194775991, https://openalex.org/W2964110616, https://openalex.org/W3097345069, https://openalex.org/W3197478142, https://openalex.org/W7027429494, https://openalex.org/W2147880316, https://openalex.org/W4253187718, https://openalex.org/W1976085885, https://openalex.org/W2963242190, https://openalex.org/W3099330747, https://openalex.org/W3007328579 |
| referenced_works_count | 30 |
| abstract_inverted_index.a | 19, 59, 63, 74, 81, 98, 102, 146, 226, 232, 251 |
| abstract_inverted_index.To | 50 |
| abstract_inverted_index.by | 12, 210 |
| abstract_inverted_index.in | 18, 54, 73, 116, 176, 187 |
| abstract_inverted_index.it | 121 |
| abstract_inverted_index.of | 4, 27, 43, 70, 94, 134, 159, 184, 198, 207, 214, 236, 240, 262 |
| abstract_inverted_index.on | 33 |
| abstract_inverted_index.to | 1, 66, 90, 124, 151, 180 |
| abstract_inverted_index.we | 57, 79 |
| abstract_inverted_index.The | 216 |
| abstract_inverted_index.and | 7, 15, 25, 77, 120, 164, 196, 244, 266, 270 |
| abstract_inverted_index.are | 37, 46 |
| abstract_inverted_index.for | 86, 274 |
| abstract_inverted_index.has | 272 |
| abstract_inverted_index.new | 82 |
| abstract_inverted_index.not | 47 |
| abstract_inverted_index.our | 160, 221, 247, 255 |
| abstract_inverted_index.the | 2, 13, 23, 34, 40, 68, 92, 109, 113, 125, 131, 135, 152, 156, 165, 171, 177, 182, 185, 194, 199, 237, 260, 263, 267 |
| abstract_inverted_index.via | 128 |
| abstract_inverted_index.was | 106, 118, 122, 138, 149, 162, 168, 174 |
| abstract_inverted_index.also | 271 |
| abstract_inverted_index.from | 259 |
| abstract_inverted_index.into | 108 |
| abstract_inverted_index.loss | 3 |
| abstract_inverted_index.rate | 230 |
| abstract_inverted_index.sets | 213 |
| abstract_inverted_index.that | 61, 220 |
| abstract_inverted_index.this | 55 |
| abstract_inverted_index.used | 62 |
| abstract_inverted_index.were | 202 |
| abstract_inverted_index.with | 101, 250 |
| abstract_inverted_index.word | 228 |
| abstract_inverted_index.Owing | 0 |
| abstract_inverted_index.added | 150 |
| abstract_inverted_index.based | 32 |
| abstract_inverted_index.error | 229 |
| abstract_inverted_index.input | 123 |
| abstract_inverted_index.lower | 227 |
| abstract_inverted_index.model | 36, 84, 137, 161, 173, 201, 224, 234, 248, 256 |
| abstract_inverted_index.other | 275 |
| abstract_inverted_index.solve | 51 |
| abstract_inverted_index.speed | 26 |
| abstract_inverted_index.then, | 78 |
| abstract_inverted_index.these | 52 |
| abstract_inverted_index.thus, | 112, 155 |
| abstract_inverted_index.types | 206 |
| abstract_inverted_index.using | 141, 246 |
| abstract_inverted_index.First, | 89 |
| abstract_inverted_index.blocks | 127 |
| abstract_inverted_index.caused | 11 |
| abstract_inverted_index.higher | 238 |
| abstract_inverted_index.method | 60 |
| abstract_inverted_index.model, | 76 |
| abstract_inverted_index.model; | 111 |
| abstract_inverted_index.models | 209 |
| abstract_inverted_index.speech | 29, 44, 87, 95, 117, 222, 241 |
| abstract_inverted_index.study, | 56 |
| abstract_inverted_index.weight | 143 |
| abstract_inverted_index.Second, | 145 |
| abstract_inverted_index.ability | 133, 158 |
| abstract_inverted_index.adopted | 175 |
| abstract_inverted_index.against | 204 |
| abstract_inverted_index.because | 39, 235 |
| abstract_inverted_index.blocks, | 154 |
| abstract_inverted_index.capsule | 64, 99, 153, 252, 264 |
| abstract_inverted_index.current | 28 |
| abstract_inverted_index.dynamic | 103, 142 |
| abstract_inverted_index.feature | 9, 71, 96, 242 |
| abstract_inverted_index.improve | 67, 91 |
| abstract_inverted_index.mapping | 157 |
| abstract_inverted_index.network | 65, 100, 148, 179, 265 |
| abstract_inverted_index.pooling | 16 |
| abstract_inverted_index.promote | 181 |
| abstract_inverted_index.results | 218 |
| abstract_inverted_index.routing | 104 |
| abstract_inverted_index.shallow | 41 |
| abstract_inverted_index.signals | 45 |
| abstract_inverted_index.through | 190 |
| abstract_inverted_index.without | 231 |
| abstract_inverted_index.Finally, | 193 |
| abstract_inverted_index.accuracy | 24, 69, 93, 239 |
| abstract_inverted_index.achieved | 225 |
| abstract_inverted_index.decoding | 178 |
| abstract_inverted_index.encoder, | 269 |
| abstract_inverted_index.enhanced | 140 |
| abstract_inverted_index.features | 42 |
| abstract_inverted_index.improved | 163 |
| abstract_inverted_index.language | 233 |
| abstract_inverted_index.learning | 132, 245 |
| abstract_inverted_index.multiple | 212 |
| abstract_inverted_index.network, | 22 |
| abstract_inverted_index.network. | 253 |
| abstract_inverted_index.proposed | 80, 200 |
| abstract_inverted_index.reduced. | 169 |
| abstract_inverted_index.residual | 147 |
| abstract_inverted_index.training | 166 |
| abstract_inverted_index.vectors; | 130 |
| abstract_inverted_index.verified | 203 |
| abstract_inverted_index.advantage | 261 |
| abstract_inverted_index.benefited | 258 |
| abstract_inverted_index.conformer | 35, 110, 126, 268 |
| abstract_inverted_index.different | 188, 205 |
| abstract_inverted_index.effective | 5 |
| abstract_inverted_index.mechanism | 105 |
| abstract_inverted_index.modeling. | 192 |
| abstract_inverted_index.potential | 273 |
| abstract_inverted_index.problems, | 53 |
| abstract_inverted_index.updating. | 144 |
| abstract_inverted_index.completely | 48 |
| abstract_inverted_index.difficulty | 167 |
| abstract_inverted_index.directions | 189 |
| abstract_inverted_index.end-to-end | 83 |
| abstract_inverted_index.extracted. | 49 |
| abstract_inverted_index.extraction | 10, 72, 243 |
| abstract_inverted_index.hypotheses | 186 |
| abstract_inverted_index.incomplete | 8 |
| abstract_inverted_index.influenced | 38 |
| abstract_inverted_index.introduced | 107 |
| abstract_inverted_index.operations | 17 |
| abstract_inverted_index.performing | 211 |
| abstract_inverted_index.preserved, | 119 |
| abstract_inverted_index.processing | 30 |
| abstract_inverted_index.researched | 58 |
| abstract_inverted_index.robustness | 197 |
| abstract_inverted_index.structural | 114 |
| abstract_inverted_index.consistency | 183 |
| abstract_inverted_index.convolution | 14, 20 |
| abstract_inverted_index.extraction, | 97 |
| abstract_inverted_index.information | 6, 115 |
| abstract_inverted_index.recognition | 208, 223 |
| abstract_inverted_index.sequestered | 129 |
| abstract_inverted_index.subsampling | 21 |
| abstract_inverted_index.Furthermore, | 170, 254 |
| abstract_inverted_index.architecture | 85, 249, 257 |
| abstract_inverted_index.demonstrated | 219 |
| abstract_inverted_index.experimental | 217 |
| abstract_inverted_index.experiments. | 215 |
| abstract_inverted_index.recognition. | 88 |
| abstract_inverted_index.applications. | 277 |
| abstract_inverted_index.architectures | 31 |
| abstract_inverted_index.bidirectional | 191 |
| abstract_inverted_index.effectiveness | 195 |
| abstract_inverted_index.significantly | 139 |
| abstract_inverted_index.bi-transformer | 172 |
| abstract_inverted_index.speech-related | 276 |
| abstract_inverted_index.conformed-based | 136 |
| abstract_inverted_index.conformer-based | 75 |
| cited_by_percentile_year.max | 97 |
| cited_by_percentile_year.min | 89 |
| corresponding_author_ids | https://openalex.org/A5025048527 |
| countries_distinct_count | 1 |
| institutions_distinct_count | 2 |
| corresponding_institution_ids | https://openalex.org/I9224756 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/4 |
| sustainable_development_goals[0].score | 0.4300000071525574 |
| sustainable_development_goals[0].display_name | Quality Education |
| citation_normalized_percentile.value | 0.75075963 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |