{"id":"https://openalex.org/W4406461426","doi":"https://doi.org/10.1109/slt61566.2024.10832231","title":"Improving Transducer-Based Spoken Language Understanding With Self-Conditioned CTC and Knowledge Transfer","display_name":"Improving Transducer-Based Spoken Language Understanding With Self-Conditioned CTC and Knowledge Transfer","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461426","doi":"https://doi.org/10.1109/slt61566.2024.10832231"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832231","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832231","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5113145191","display_name":"Vishal Sunder","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Vishal Sunder","raw_affiliation_strings":["The Ohio State University"],"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056667180","display_name":"Eric Fosler\u2010Lussier","orcid":"https://orcid.org/0000-0001-8004-5169"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Fosler-Lussier","raw_affiliation_strings":["The Ohio State University"],"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5113145191"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23788877,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1123","last_page":"1130"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9990000128746033,"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/T12031","display_name":"Speech and dialogue systems","score":0.9983999729156494,"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":0.7485237717628479},{"id":"https://openalex.org/keywords/transducer","display_name":"Transducer","score":0.559881865978241},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.5319127440452576},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5112605094909668},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4033568501472473},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39958739280700684},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.17666813731193542},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11019554734230042}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7485237717628479},{"id":"https://openalex.org/C56318395","wikidata":"https://www.wikidata.org/wiki/Q215928","display_name":"Transducer","level":2,"score":0.559881865978241},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.5319127440452576},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5112605094909668},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4033568501472473},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39958739280700684},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.17666813731193542},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11019554734230042}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832231","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832231","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2327501763","https://openalex.org/W2526425061","https://openalex.org/W2936774411","https://openalex.org/W2937780860","https://openalex.org/W3016006013","https://openalex.org/W3090731342","https://openalex.org/W3097777922","https://openalex.org/W3097964672","https://openalex.org/W3100460087","https://openalex.org/W3155162503","https://openalex.org/W3161000786","https://openalex.org/W3174008653","https://openalex.org/W3197140813","https://openalex.org/W3211224152","https://openalex.org/W4200113972","https://openalex.org/W4210673375","https://openalex.org/W4224916448","https://openalex.org/W4226315417","https://openalex.org/W4296068780","https://openalex.org/W4296070421","https://openalex.org/W4297727296","https://openalex.org/W4372259817","https://openalex.org/W4372341986","https://openalex.org/W4375868951","https://openalex.org/W4385245566","https://openalex.org/W4385571436","https://openalex.org/W4385574035","https://openalex.org/W4385822624","https://openalex.org/W4385822705","https://openalex.org/W4385823346","https://openalex.org/W4385823351","https://openalex.org/W4386566728","https://openalex.org/W4387390320","https://openalex.org/W6797942755","https://openalex.org/W6803378298","https://openalex.org/W6839026989","https://openalex.org/W6847219037","https://openalex.org/W6847363464","https://openalex.org/W6858015354"],"related_works":["https://openalex.org/W2012283803","https://openalex.org/W4384820447","https://openalex.org/W2072454424","https://openalex.org/W2117438306","https://openalex.org/W2185942010","https://openalex.org/W2260725127","https://openalex.org/W2004297762","https://openalex.org/W1992056405","https://openalex.org/W1966826629","https://openalex.org/W3204019825"],"abstract_inverted_index":{"In":[0],"this":[1,93,121],"paper,":[2],"we":[3,48],"propose":[4],"to":[5,35,124],"improve":[6,84],"end-to-end":[7],"(E2E)":[8],"spoken":[9],"language":[10],"understand":[11],"(SLU)":[12],"in":[13],"an":[14,36],"RNN":[15],"transducer":[16],"model":[17,32,40,94],"(RNN-T)":[18],"by":[19,60,87],"incorporating":[20],"a":[21,109],"joint":[22,67],"self-conditioned":[23],"CTC":[24,62],"automatic":[25],"speech":[26],"recognition":[27],"(ASR)":[28],"objective.":[29],"Our":[30,101],"proposed":[31,102],"is":[33,54,122],"akin":[34],"E2E":[37],"differentiable":[38],"cascaded":[39],"which":[41],"performs":[42],"ASR":[43,58,70],"and":[44,47,71,117,140],"SLU":[45,52,72,74,80,129],"sequentially":[46],"ensure":[49],"that":[50],"the":[51,57,85,89,96,114,118,126],"task":[53,59],"conditioned":[55],"on":[56,113],"having":[61],"self":[63],"conditioning.":[64],"This":[65],"novel":[66],"modeling":[68],"of":[69,92,108,120],"improves":[73],"performance":[75,86],"significantly":[76,151],"over":[77,136],"just":[78],"using":[79],"optimization.":[81],"We":[82],"further":[83],"aligning":[88],"acoustic":[90],"embeddings":[91,116],"with":[95,145,150],"semantically":[97],"richer":[98],"BERT":[99],"model.":[100],"knowledge":[103],"transfer":[104],"strategy":[105],"makes":[106],"use":[107],"bag-of-entity":[110],"prediction":[111],"layer":[112],"aligned":[115],"output":[119],"used":[123],"condition":[125],"RNN-T":[127],"based":[128],"decoding.":[130],"These":[131],"techniques":[132],"show":[133],"significant":[134],"improvement":[135],"several":[137],"strong":[138],"baselines":[139],"can":[141],"perform":[142],"at":[143],"par":[144],"large":[146],"models":[147],"like":[148],"Whisper":[149],"fewer":[152],"parameters.":[153]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}