{"id":"https://openalex.org/W4385822453","doi":"https://doi.org/10.21437/interspeech.2023-1432","title":"SememeASR: Boosting Performance of End-to-End Speech Recognition against Domain and Long-Tailed Data Shift with Sememe Semantic Knowledge","display_name":"SememeASR: Boosting Performance of End-to-End Speech Recognition against Domain and Long-Tailed Data Shift with Sememe Semantic Knowledge","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822453","doi":"https://doi.org/10.21437/interspeech.2023-1432"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-1432","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-1432","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2309.01437","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040092764","display_name":"Jiaxu Zhu","orcid":"https://orcid.org/0000-0003-0988-5493"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaxu Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048029954","display_name":"Changhe Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Changhe Song","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09711774,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3272","last_page":"3276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9807000160217285,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9394000172615051,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7646886706352234},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6930580139160156},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.6495801210403442},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.537652850151062},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5304500460624695},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5149715542793274},{"id":"https://openalex.org/keywords/semantic-memory","display_name":"Semantic memory","score":0.4140596389770508},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09470227360725403}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7646886706352234},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6930580139160156},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.6495801210403442},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.537652850151062},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5304500460624695},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5149715542793274},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.4140596389770508},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09470227360725403},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2023-1432","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-1432","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2309.01437","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.01437","pdf_url":"https://arxiv.org/pdf/2309.01437","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2309.01437","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.01437","pdf_url":"https://arxiv.org/pdf/2309.01437","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385822453.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W4231274751","https://openalex.org/W1549363203","https://openalex.org/W2154063878","https://openalex.org/W2556012038","https://openalex.org/W1489772951","https://openalex.org/W1538046993","https://openalex.org/W4239293476","https://openalex.org/W1566995892"],"abstract_inverted_index":{"Recently,":[0],"excellent":[1],"progress":[2],"has":[3],"been":[4],"made":[5],"in":[6,19,56],"speech":[7,42,87],"recognition.":[8,88],"However,":[9],"pure":[10],"data-driven":[11,30],"approaches":[12,27,31],"have":[13],"struggled":[14],"to":[15,41,47,62],"solve":[16],"the":[17,48,52,64,77,84,100,108],"problem":[18],"domain-mismatch":[20],"and":[21,59,106],"long-tailed":[22,104],"data.":[23],"Considering":[24],"that":[25,76,95],"knowledge-driven":[26],"can":[28,82,98],"help":[29],"alleviate":[32],"their":[33],"flaws,":[34],"we":[35],"introduce":[36],"sememe-based":[37],"semantic":[38,54,66],"knowledge":[39,97],"information":[40,67,81],"recognition":[43,102],"(SememeASR).":[44],"Sememe,":[45],"according":[46],"linguistic":[49],"definition,":[50],"is":[51,60],"minimum":[53],"unit":[55],"a":[57],"language":[58],"able":[61],"represent":[63],"implicit":[65],"behind":[68],"each":[69],"word":[70],"very":[71],"well.":[72],"Our":[73],"experiments":[74,93],"show":[75,94],"introduction":[78],"of":[79,86,103],"sememe":[80,96],"improve":[83,99],"effectiveness":[85],"In":[89],"addition,":[90],"our":[91],"further":[92],"model's":[101,109],"data":[105],"enhance":[107],"domain":[110],"generalization":[111],"ability.":[112]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}