{"id":"https://openalex.org/W4372347505","doi":"https://doi.org/10.1109/icassp49357.2023.10096827","title":"Bridging Speech and Textual Pre-Trained Models With Unsupervised ASR","display_name":"Bridging Speech and Textual Pre-Trained Models With Unsupervised ASR","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372347505","doi":"https://doi.org/10.1109/icassp49357.2023.10096827"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096827","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096827","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5008336983","display_name":"Jiatong Shi","orcid":"https://orcid.org/0000-0002-9050-8304"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jiatong Shi","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059902893","display_name":"Chan-Jan Hsu","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chan-Jan Hsu","raw_affiliation_strings":["National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111114748","display_name":"Ho-Lam Chung","orcid":"https://orcid.org/0000-0003-3847-0166"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Holam Chung","raw_affiliation_strings":["National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072814956","display_name":"Dongji Gao","orcid":"https://orcid.org/0009-0006-8885-3084"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dongji Gao","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059858850","display_name":"Leibny Paola Garcia","orcid":"https://orcid.org/0000-0002-7449-5726"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paola Garcia","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084509956","display_name":"Ann Lee","orcid":"https://orcid.org/0000-0003-4300-9032"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ann Lee","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-Yi Lee","raw_affiliation_strings":["National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5008336983"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":1.2238,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.82725593,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"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":0.9998999834060669,"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":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","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":0.9994000196456909,"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":0.8680011630058289},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.6354939937591553},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6055744290351868},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.600476861000061},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5878012180328369},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5737935900688171},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5493547320365906},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5045512914657593},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5028802752494812},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.47037047147750854},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.43325328826904297}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8680011630058289},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.6354939937591553},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6055744290351868},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.600476861000061},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5878012180328369},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5737935900688171},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5493547320365906},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5045512914657593},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5028802752494812},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.47037047147750854},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.43325328826904297},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096827","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096827","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6000000238418579,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W2058094241","https://openalex.org/W2146334809","https://openalex.org/W2557764419","https://openalex.org/W2766219058","https://openalex.org/W2888302696","https://openalex.org/W2896457183","https://openalex.org/W2963748441","https://openalex.org/W2964079874","https://openalex.org/W2972706021","https://openalex.org/W2981022124","https://openalex.org/W2988736778","https://openalex.org/W2995181338","https://openalex.org/W3015419784","https://openalex.org/W3016006013","https://openalex.org/W3036601975","https://openalex.org/W3037217258","https://openalex.org/W3097787369","https://openalex.org/W3100460087","https://openalex.org/W3148001440","https://openalex.org/W3161223924","https://openalex.org/W3163793923","https://openalex.org/W3164045210","https://openalex.org/W3196509775","https://openalex.org/W3197580070","https://openalex.org/W3207222250","https://openalex.org/W3207558756","https://openalex.org/W3217767527","https://openalex.org/W4221146627","https://openalex.org/W4221155340","https://openalex.org/W4224925047","https://openalex.org/W4226162428","https://openalex.org/W4285250921","https://openalex.org/W4286849919","https://openalex.org/W4287173589","https://openalex.org/W4297841398","https://openalex.org/W4297841571","https://openalex.org/W4319862670","https://openalex.org/W4372349162","https://openalex.org/W6630875275","https://openalex.org/W6755207826","https://openalex.org/W6757699909","https://openalex.org/W6770514103","https://openalex.org/W6780218876","https://openalex.org/W6795952400","https://openalex.org/W6803092890","https://openalex.org/W6804414493","https://openalex.org/W6810259195","https://openalex.org/W6849453057","https://openalex.org/W6849880362"],"related_works":["https://openalex.org/W4388870064","https://openalex.org/W4235186151","https://openalex.org/W2056057048","https://openalex.org/W2054685365","https://openalex.org/W2272354214","https://openalex.org/W2120383820","https://openalex.org/W2043010663","https://openalex.org/W2667588871","https://openalex.org/W4248308508","https://openalex.org/W2941608206"],"abstract_inverted_index":{"Spoken":[0],"language":[1],"understanding":[2],"(SLU)":[3],"is":[4,131],"a":[5,62,100],"task":[6],"aiming":[7],"to":[8,34,92],"extract":[9],"high-level":[10],"semantics":[11],"from":[12,124],"spoken":[13,153],"utterances.":[14],"Previous":[15],"works":[16],"have":[17,30],"investigated":[18],"the":[19,41,57,122,144,158,162],"use":[20,93],"of":[21,40,56,146],"speech":[22,45,70,96,108,125,138],"self-supervised":[23,126],"models":[24],"and":[25,47,71,109,139],"textual":[26,72,110,140],"pre-trained":[27,73,80,111,141],"models,":[28,74,142],"which":[29],"shown":[31,132],"reasonable":[32],"improvements":[33],"various":[35,83],"SLU":[36,149],"tasks.":[37,150],"However,":[38],"because":[39],"mismatched":[42],"modalities":[43,105],"between":[44,137],"signals":[46],"text":[48],"tokens,":[49],"previous":[50],"methods":[51],"usually":[52],"need":[53],"complex":[54],"designs":[55],"frameworks.":[58],"This":[59],"work":[60],"proposes":[61],"simple":[63],"yet":[64],"efficient":[65,135],"unsupervised":[66,78,94,117],"paradigm":[67],"that":[68,102,116],"connects":[69],"resulting":[75],"in":[76,85,107],"an":[77,134],"speech-to-semantic":[79],"model":[81],"for":[82],"tasks":[84],"SLU.":[86],"To":[87],"be":[88],"specific,":[89],"we":[90,156],"propose":[91],"automatic":[95],"recognition":[97],"(ASR)":[98],"as":[99,133],"connector":[101,136],"bridges":[103],"different":[104,148],"used":[106],"models.":[112,127],"Our":[113],"experiments":[114],"show":[115],"ASR":[118],"itself":[119],"can":[120],"improve":[121],"representations":[123],"More":[128],"importantly,":[129],"it":[130],"improving":[143],"performances":[145],"five":[147],"Notably,":[151],"on":[152],"question":[154],"answering,":[155],"reach":[157],"state-of-the-art":[159],"result":[160],"over":[161],"challenging":[163],"NMSQA":[164],"benchmark.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}