{"id":"https://openalex.org/W3096109555","doi":"https://doi.org/10.21437/interspeech.2020-1570","title":"SpeechBERT: An Audio-and-Text Jointly Learned Language Model for End-to-End Spoken Question Answering","display_name":"SpeechBERT: An Audio-and-Text Jointly Learned Language Model for End-to-End Spoken Question Answering","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096109555","doi":"https://doi.org/10.21437/interspeech.2020-1570","mag":"3096109555"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1570","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5058729228","display_name":"Yung-Sung Chuang","orcid":"https://orcid.org/0000-0002-1723-5063"},"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":"Yung-Sung Chuang","raw_affiliation_strings":["College of Electrical Engineering and Computer Science, National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043302919","display_name":"Chi-Liang Liu","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":"Chi-Liang Liu","raw_affiliation_strings":["College of Electrical Engineering and Computer Science, National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","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":["College of Electrical Engineering and Computer Science, National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044010123","display_name":"Lin-shan Lee","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":"Lin-shan Lee","raw_affiliation_strings":["College of Electrical Engineering and Computer Science, National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":8.2616,"has_fulltext":false,"cited_by_count":83,"citation_normalized_percentile":{"value":0.98072779,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4168","last_page":"4172"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980000257492065,"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":0.9980000257492065,"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":0.9976999759674072,"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":0.996999979019165,"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":0.8068026304244995},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6199893355369568},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.531035304069519},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5218707323074341},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.49767521023750305},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.42752158641815186},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.425667941570282},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4197840690612793},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3214460611343384}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8068026304244995},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6199893355369568},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.531035304069519},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5218707323074341},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.49767521023750305},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.42752158641815186},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.425667941570282},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4197840690612793},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3214460611343384},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-1570","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8299999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1984076147","https://openalex.org/W2525778437","https://openalex.org/W2551396370","https://openalex.org/W2802557066","https://openalex.org/W2804648901","https://openalex.org/W2891229414","https://openalex.org/W2894164357","https://openalex.org/W2896457183","https://openalex.org/W2899377381","https://openalex.org/W2914120296","https://openalex.org/W2949328740","https://openalex.org/W2962854302","https://openalex.org/W2962985038","https://openalex.org/W2963039488","https://openalex.org/W2963288440","https://openalex.org/W2963323070","https://openalex.org/W2963425185","https://openalex.org/W2963571336","https://openalex.org/W2963748441","https://openalex.org/W2965373594","https://openalex.org/W2970597249","https://openalex.org/W2972584841","https://openalex.org/W2979476256","https://openalex.org/W2981991061","https://openalex.org/W2982095018","https://openalex.org/W2982223350","https://openalex.org/W3011411500","https://openalex.org/W3015265920","https://openalex.org/W3015586639","https://openalex.org/W3016006013","https://openalex.org/W3016262400","https://openalex.org/W3096485810","https://openalex.org/W4294170691"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3179968364","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W3204607391","https://openalex.org/W2964413124","https://openalex.org/W2916997151","https://openalex.org/W3113264705","https://openalex.org/W2949174760"],"abstract_inverted_index":{"While":[0],"various":[1,40],"end-to-end":[2,28,79,100,116],"models":[3],"for":[4,39,124,134],"spoken":[5,29,127],"language":[6,128],"understanding":[7,129],"tasks":[8,130],"have":[9],"been":[10],"explored":[11],"recently,":[12],"this":[13],"paper":[14],"is":[15],"probably":[16],"the":[17,23,34,55,62,78,98,103,113,118],"first":[18],"known":[19],"attempt":[20],"to":[21,83,86,112],"challenge":[22],"very":[24,35],"difficult":[25],"task":[26],"of":[27,58,90,115],"question":[30,65],"answering":[31,66],"(SQA).Learning":[32],"from":[33],"successful":[36],"BERT":[37,133],"model":[38,53,68,80,101],"text":[41,64,136],"processing":[42,137],"tasks,":[43],"here":[44],"we":[45],"proposed":[46,99],"an":[47],"audio-and-text":[48],"jointly":[49],"learned":[50],"SpeechBERT":[51,119],"model.This":[52],"outperformed":[54],"conventional":[56],"approach":[57],"cascading":[59],"ASR":[60,72,94],"with":[61,102],"following":[63],"(TQA)":[67],"on":[69],"datasets":[70],"including":[71],"errors":[73],"in":[74],"answer":[75],"spans,":[76],"because":[77],"was":[81,109],"shown":[82],"be":[84,122],"able":[85],"extract":[87],"information":[88],"out":[89],"audio":[91],"data":[92],"before":[93],"produced":[95],"errors.When":[96],"ensembling":[97],"cascade":[104],"architecture,":[105],"even":[106],"better":[107],"performance":[108],"achieved.In":[110],"addition":[111],"potential":[114],"SQA,":[117],"can":[120],"also":[121],"considered":[123],"many":[125,135],"other":[126],"just":[131],"as":[132],"tasks.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":22},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":23},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}