{"id":"https://openalex.org/W4221146627","doi":"https://doi.org/10.21437/interspeech.2022-612","title":"DUAL: Discrete Spoken Unit Adaptive Learning for Textless Spoken Question Answering","display_name":"DUAL: Discrete Spoken Unit Adaptive Learning for Textless Spoken Question Answering","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4221146627","doi":"https://doi.org/10.21437/interspeech.2022-612"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-612","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-612","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5108124525","display_name":"Guan-Ting Lin","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":"Guan-Ting Lin","raw_affiliation_strings":["National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058729228","display_name":"Yung-Sung Chuang","orcid":"https://orcid.org/0000-0002-1723-5063"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yung-Sung Chuang","raw_affiliation_strings":["Massachusetts Institute of Technology, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"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":"Ho-Lam Chung","raw_affiliation_strings":["National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082726995","display_name":"Shuwen Yang","orcid":"https://orcid.org/0000-0001-7728-162X"},"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":"Shu-wen Yang","raw_affiliation_strings":["National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065176594","display_name":"Hsuan-Jui Chen","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":"Hsuan-Jui Chen","raw_affiliation_strings":["National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102446503","display_name":"Shuyan Annie Dong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuyan Annie Dong","raw_affiliation_strings":["Meta AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029566548","display_name":"Shang-Wen Li","orcid":"https://orcid.org/0000-0003-0656-9874"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shang-Wen Li","raw_affiliation_strings":["Meta AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101170706","display_name":"Abdelrahman Mohamed","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abdelrahman Mohamed","raw_affiliation_strings":["Meta AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]},{"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":["National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taiwan","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":["National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.661,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.85671879,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5165","last_page":"5169"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9923999905586243,"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":0.9923999905586243,"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":0.9851999878883362,"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":0.9498000144958496,"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/dual","display_name":"Dual (grammatical number)","score":0.6777525544166565},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6578372716903687},{"id":"https://openalex.org/keywords/unit","display_name":"Unit (ring theory)","score":0.5469227433204651},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.47446972131729126},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4378983974456787},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4354848861694336},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4294630289077759},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33963894844055176},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1475248634815216},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10622254014015198},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.050158023834228516}],"concepts":[{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6777525544166565},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6578372716903687},{"id":"https://openalex.org/C122637931","wikidata":"https://www.wikidata.org/wiki/Q118084","display_name":"Unit (ring theory)","level":2,"score":0.5469227433204651},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.47446972131729126},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4378983974456787},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4354848861694336},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4294630289077759},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33963894844055176},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1475248634815216},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10622254014015198},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.050158023834228516},{"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.2022-612","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-612","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2747874407","https://openalex.org/W2885485938","https://openalex.org/W2896457183","https://openalex.org/W2962854302","https://openalex.org/W2962904995","https://openalex.org/W2963446094","https://openalex.org/W2963748441","https://openalex.org/W3015468748","https://openalex.org/W3016191377","https://openalex.org/W3036601975","https://openalex.org/W3092945658","https://openalex.org/W3096109555","https://openalex.org/W3104570641","https://openalex.org/W3134307371","https://openalex.org/W3136270197","https://openalex.org/W3140429000","https://openalex.org/W3148001440","https://openalex.org/W3153592532","https://openalex.org/W3163162786","https://openalex.org/W3167533889","https://openalex.org/W3169320628","https://openalex.org/W3180374548","https://openalex.org/W3191850102","https://openalex.org/W3197580070","https://openalex.org/W3198802556","https://openalex.org/W3213234281","https://openalex.org/W3213873715","https://openalex.org/W4226089239","https://openalex.org/W4286984129","https://openalex.org/W4287854499","https://openalex.org/W4394671563"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912","https://openalex.org/W4288102755","https://openalex.org/W3159777597","https://openalex.org/W198220271"],"abstract_inverted_index":{"Spoken":[0,119],"Question":[1],"Answering":[2],"(SQA)":[3],"is":[4,17,106],"to":[5,24,44,56,68,84,97,112,169,181],"find":[6],"the":[7,25,28,66,69,98,132],"answer":[8],"from":[9,27,145],"a":[10,14,150],"spoken":[11,139,146],"document":[12],"given":[13],"question,":[15],"which":[16],"crucial":[18],"for":[19,58,127,156],"personal":[20],"assistants":[21],"when":[22],"replying":[23],"queries":[26],"users.Existing":[29],"SQA":[30,99,101,133,152],"methods":[31],"all":[32,90],"rely":[33],"on":[34],"Automatic":[35],"Speech":[36],"Recognition":[37],"(ASR)":[38],"transcripts.Not":[39],"only":[40],"does":[41],"ASR":[42,82,103,174],"need":[43],"be":[45,79,113,142,188],"trained":[46],"with":[47,158],"massive":[48],"annotated":[49],"data":[50,126,157],"that":[51,77,164],"are":[52],"time":[53,136],"and":[54,129,175,179,185],"cost-prohibitive":[55],"collect":[57],"low-resourced":[59],"languages,":[60],"but":[61],"more":[62,159],"importantly,":[63],"very":[64,114],"often":[65],"answers":[67,140],"questions":[70],"include":[71],"name":[72],"entities":[73],"or":[74],"out-of-vocabulary":[75],"words":[76,95],"cannot":[78],"recognized":[80],"correctly.Also,":[81],"aims":[83],"minimize":[85],"recognition":[86],"errors":[87],"equally":[88],"over":[89],"words,":[91],"including":[92],"many":[93],"function":[94],"irrelevant":[96],"task.Therefore,":[100],"without":[102],"transcripts":[104],"(textless)":[105],"always":[107],"highly":[108],"desired,":[109],"although":[110],"known":[111],"difficult.This":[115],"work":[116],"proposes":[117],"Discrete":[118],"Unit":[120],"Adaptive":[121],"Learning":[122],"(DUAL),":[123],"leveraging":[124],"unlabeled":[125],"pre-training":[128],"finetuned":[130],"by":[131,172],"downstream":[134],"task.The":[135],"intervals":[137],"of":[138],"can":[141],"directly":[143],"predicted":[144],"documents.We":[147],"also":[148],"release":[149],"new":[151],"benchmark":[153],"corpus,":[154],"NMSQA,":[155],"realistic":[160],"scenarios.We":[161],"empirically":[162],"showed":[163],"DUAL":[165],"yields":[166],"results":[167],"comparable":[168],"those":[170],"obtained":[171],"cascading":[173],"text":[176],"QA":[177],"model":[178,186],"robust":[180],"real-world":[182],"data.Our":[183],"code":[184],"will":[187],"open-sourced":[189],"1":[190],".":[191]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}