{"id":"https://openalex.org/W4408353570","doi":"https://doi.org/10.1109/icassp49660.2025.10889025","title":"Joint Automatic Speech Recognition And Structure Learning For Better Speech Understanding","display_name":"Joint Automatic Speech Recognition And Structure Learning For Better Speech Understanding","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353570","doi":"https://doi.org/10.1109/icassp49660.2025.10889025"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889025","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102311417","display_name":"Jianguo Hu","orcid":"https://orcid.org/0009-0007-5988-6888"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiliang Hu","raw_affiliation_strings":["Wuhan University,Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Wuhan University,Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering,Wuhan,China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002584135","display_name":"Zuchao Li","orcid":"https://orcid.org/0000-0003-0436-8446"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zuchao Li","raw_affiliation_strings":["Wuhan University,School of Computer Science,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Wuhan University,School of Computer Science,Wuhan,China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083598817","display_name":"Mengjia Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210129465","display_name":"Wuhan Ship Development & Design Institute","ror":"https://ror.org/02mcdae06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210129465"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengjia Shen","raw_affiliation_strings":["Wuhan Second Ship Design and Research Institute,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Wuhan Second Ship Design and Research Institute,Wuhan,China","institution_ids":["https://openalex.org/I4210129465"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074448137","display_name":"Haojun Ai","orcid":"https://orcid.org/0000-0002-4172-5070"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haojun Ai","raw_affiliation_strings":["Wuhan University,Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Wuhan University,Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering,Wuhan,China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053726259","display_name":"Sheng Li","orcid":"https://orcid.org/0000-0001-7636-3797"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sheng Li","raw_affiliation_strings":["National Institute of Information and Communications Technology,Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology,Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5092138453","display_name":"Jun Zhang","orcid":"https://orcid.org/0009-0005-4590-1392"},"institutions":[{"id":"https://openalex.org/I4210129465","display_name":"Wuhan Ship Development & Design Institute","ror":"https://ror.org/02mcdae06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210129465"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Zhang","raw_affiliation_strings":["Wuhan Second Ship Design and Research Institute,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Wuhan Second Ship Design and Research Institute,Wuhan,China","institution_ids":["https://openalex.org/I4210129465"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102311417"],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0204278,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9708999991416931,"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":0.9708999991416931,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7877097725868225},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7320783138275146},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6774793863296509},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4624844193458557},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.42122653126716614},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4123919606208801},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39785367250442505},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11584898829460144}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7877097725868225},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7320783138275146},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6774793863296509},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4624844193458557},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.42122653126716614},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4123919606208801},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39785367250442505},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11584898829460144},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889025","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2798304389","https://openalex.org/W2963022746","https://openalex.org/W2998230451","https://openalex.org/W3015686596","https://openalex.org/W3095918555","https://openalex.org/W3100460087","https://openalex.org/W3176549752","https://openalex.org/W3211278025","https://openalex.org/W3211443367","https://openalex.org/W3213029956","https://openalex.org/W3217767527","https://openalex.org/W4221139374","https://openalex.org/W4226103796","https://openalex.org/W4283067311","https://openalex.org/W4287887773","https://openalex.org/W4296070421","https://openalex.org/W4319862410","https://openalex.org/W4372260611","https://openalex.org/W4385571338","https://openalex.org/W4385574035","https://openalex.org/W4385822407","https://openalex.org/W4391021713","https://openalex.org/W4401042470","https://openalex.org/W6691509046","https://openalex.org/W6755207826","https://openalex.org/W6771467084","https://openalex.org/W6778883912","https://openalex.org/W6801504582","https://openalex.org/W6843814252","https://openalex.org/W6847363464","https://openalex.org/W6851766456","https://openalex.org/W6854272408","https://openalex.org/W6858427178"],"related_works":["https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W2041273198","https://openalex.org/W1599055764","https://openalex.org/W2131711534","https://openalex.org/W2149163000","https://openalex.org/W2962858469","https://openalex.org/W2289873871","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"Spoken":[0],"language":[1],"understanding":[2],"(SLU)":[3],"is":[4,33],"a":[5,23,47],"structure":[6,52],"prediction":[7],"task":[8,25],"in":[9,107],"the":[10,84,89,103,119],"field":[11],"of":[12],"speech.":[13],"Recently,":[14],"many":[15],"works":[16],"on":[17,61,76,118],"SLU":[18,58],"that":[19,96],"treat":[20],"it":[21],"as":[22],"sequence-to-sequence":[24,105],"have":[26],"achieved":[27],"great":[28],"success.":[29],"However,":[30],"This":[31],"method":[32,99,106],"not":[34,100],"suitable":[35],"for":[36],"simultaneous":[37],"speech":[38,49,67],"recognition":[39,50,79],"and":[40,51,68,80,88,110],"understanding.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45],"propose":[46],"joint":[48],"learning":[53],"framework":[54],"(JSRSL),":[55],"an":[56],"end-to-end":[57],"model":[59],"based":[60],"span,":[62],"which":[63],"can":[64],"accurately":[65],"transcribe":[66],"extract":[69],"structured":[70],"content":[71],"simultaneously.":[72],"We":[73],"conduct":[74],"experiments":[75],"name":[77],"entity":[78],"intent":[81],"classification":[82],"using":[83],"Chinese":[85],"dataset":[86,91],"AISHELL-NER":[87],"English":[90],"SLURP.":[92],"The":[93],"results":[94],"show":[95],"our":[97],"proposed":[98],"only":[101],"outperforms":[102],"traditional":[104],"both":[108],"transcription":[109],"extraction":[111],"capabilities":[112],"but":[113],"also":[114],"achieves":[115],"state-of-the-art":[116],"performance":[117],"two":[120],"datasets.":[121]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}