{"id":"https://openalex.org/W3206694069","doi":"https://doi.org/10.1109/taslp.2021.3120638","title":"Audio-Aware Spoken Multiple-Choice Question Answering With Pre-Trained Language Models","display_name":"Audio-Aware Spoken Multiple-Choice Question Answering With Pre-Trained Language Models","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3206694069","doi":"https://doi.org/10.1109/taslp.2021.3120638","mag":"3206694069"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3120638","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3120638","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5102421526","display_name":"Chia-Chih Kuo","orcid":null},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chia-Chih Kuo","raw_affiliation_strings":["Dept. of Computer Science and Information Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science and Information Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan#TAB#","institution_ids":["https://openalex.org/I154864474"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100714445","display_name":"Kuan-Yu Chen","orcid":"https://orcid.org/0000-0001-9656-7551"},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kuan-Yu Chen","raw_affiliation_strings":["Dept. of Computer Science and Information Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan#TAB#"],"raw_orcid":"https://orcid.org/0000-0001-9656-7551","affiliations":[{"raw_affiliation_string":"Dept. of Computer Science and Information Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan#TAB#","institution_ids":["https://openalex.org/I154864474"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067529162","display_name":"Shang-Bao Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shang-Bao Luo","raw_affiliation_strings":["Dept. of Computer Science and Information Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science and Information Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan#TAB#","institution_ids":["https://openalex.org/I154864474"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102421526"],"corresponding_institution_ids":["https://openalex.org/I154864474"],"apc_list":null,"apc_paid":null,"fwci":0.42,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.70203111,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"29","issue":null,"first_page":"3170","last_page":"3179"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9991000294685364,"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":0.8437556028366089},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5868673920631409},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5698299407958984},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5465932488441467},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.5452861785888672},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.5372561812400818},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.530036449432373},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5184897184371948},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5160772204399109},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5070366859436035},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5025429725646973},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.4353407025337219},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4320676028728485}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8437556028366089},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5868673920631409},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5698299407958984},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5465932488441467},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.5452861785888672},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.5372561812400818},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.530036449432373},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5184897184371948},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5160772204399109},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5070366859436035},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5025429725646973},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.4353407025337219},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4320676028728485},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2021.3120638","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3120638","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8492084404","display_name":null,"funder_award_id":"MOST 110-2636-E-011-003","funder_id":"https://openalex.org/F4320322795","funder_display_name":"Ministry of Science and Technology, Taiwan"}],"funders":[{"id":"https://openalex.org/F4320322795","display_name":"Ministry of Science and Technology, Taiwan","ror":"https://ror.org/02kv4zf79"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":87,"referenced_works":["https://openalex.org/W14941018","https://openalex.org/W1524333225","https://openalex.org/W1614298861","https://openalex.org/W1631260214","https://openalex.org/W2126776599","https://openalex.org/W2130237711","https://openalex.org/W2131342762","https://openalex.org/W2133564696","https://openalex.org/W2140943358","https://openalex.org/W2148986421","https://openalex.org/W2153579005","https://openalex.org/W2173361515","https://openalex.org/W2181864336","https://openalex.org/W2194775991","https://openalex.org/W2250432970","https://openalex.org/W2250539671","https://openalex.org/W2250595585","https://openalex.org/W2251355301","https://openalex.org/W2252000379","https://openalex.org/W2325162016","https://openalex.org/W2493916176","https://openalex.org/W2505232340","https://openalex.org/W2514741789","https://openalex.org/W2771904183","https://openalex.org/W2789078277","https://openalex.org/W2799201288","https://openalex.org/W2802201485","https://openalex.org/W2888867175","https://openalex.org/W2896457183","https://openalex.org/W2908510526","https://openalex.org/W2919115771","https://openalex.org/W2921273687","https://openalex.org/W2923890923","https://openalex.org/W2938224028","https://openalex.org/W2942128719","https://openalex.org/W2950577311","https://openalex.org/W2962739339","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963521239","https://openalex.org/W2963900105","https://openalex.org/W2964308564","https://openalex.org/W2965373594","https://openalex.org/W2970419734","https://openalex.org/W2970597249","https://openalex.org/W2970971581","https://openalex.org/W2979826702","https://openalex.org/W2998704965","https://openalex.org/W3007382154","https://openalex.org/W3016191377","https://openalex.org/W3030163527","https://openalex.org/W3082274269","https://openalex.org/W3095902331","https://openalex.org/W3096109555","https://openalex.org/W3098824823","https://openalex.org/W3119332133","https://openalex.org/W3132537021","https://openalex.org/W4246962055","https://openalex.org/W4285719527","https://openalex.org/W4288089799","https://openalex.org/W4292779060","https://openalex.org/W4294170691","https://openalex.org/W4295312788","https://openalex.org/W4385245566","https://openalex.org/W6631362777","https://openalex.org/W6636510571","https://openalex.org/W6636811518","https://openalex.org/W6679434410","https://openalex.org/W6680532216","https://openalex.org/W6682691769","https://openalex.org/W6685536428","https://openalex.org/W6685903065","https://openalex.org/W6739901393","https://openalex.org/W6746473022","https://openalex.org/W6748333957","https://openalex.org/W6752083267","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6760359991","https://openalex.org/W6761345506","https://openalex.org/W6766673545","https://openalex.org/W6766978945","https://openalex.org/W6769243733","https://openalex.org/W6769627184","https://openalex.org/W6778883912","https://openalex.org/W6788585124","https://openalex.org/W6791280665"],"related_works":["https://openalex.org/W2114097550","https://openalex.org/W4385352507","https://openalex.org/W2918559346","https://openalex.org/W84309476","https://openalex.org/W4286904253","https://openalex.org/W4288267738","https://openalex.org/W2964413124","https://openalex.org/W4388937922","https://openalex.org/W3113264705","https://openalex.org/W2069071271"],"abstract_inverted_index":{"Spoken":[0],"multiple-choice":[1],"question":[2,15],"answering":[3],"(SMCQA)":[4],"requires":[5],"machines":[6],"to":[7,12,18,56,137],"select":[8],"the":[9,14,19,22,24,32,37,47,57,65,99,114,119,139,155,162,173,181],"correct":[10],"choice":[11],"answer":[13],"by":[16,98,169],"referring":[17],"passage,":[20,23],"where":[21],"question,":[25],"and":[26,144,196],"multiple":[27],"choices":[28],"are":[29,135],"all":[30],"in":[31,52,108,123,191],"form":[33],"of":[34,83,121,164,186],"speech.":[35],"While":[36],"audio":[38,179],"could":[39],"contain":[40],"useful":[41,140],"cues":[42,141],"for":[43],"SMCQA,":[44],"usually":[45],"only":[46,74,160],"auto-transcribed":[48,75],"text":[49,76,95],"is":[50,130,150],"utilized":[51],"model":[53],"development.":[54],"Thanks":[55],"large-scaled":[58],"pre-trained":[59],"language":[60,166],"representation":[61,105],"models,":[62],"such":[63],"as":[64],"bidirectional":[66],"encoder":[67],"representations":[68,167],"from":[69,142,178],"Transformers":[70],"(BERT),":[71],"systems":[72,103,198],"with":[73,180],"can":[77,93],"still":[78],"achieve":[79],"a":[80,146,200],"certain":[81],"level":[82],"performance.":[84],"However,":[85],"previous":[86],"studies":[87],"have":[88],"evidenced":[89],"that":[90],"acoustic-level":[91,175],"statistics":[92],"offset":[94],"inaccuracies":[96],"caused":[97],"automatic":[100],"speech":[101],"recognition":[102],"or":[104],"inadequacy":[106],"lurking":[107],"word":[109],"embedding":[110],"generators,":[111],"thereby":[112],"making":[113],"SMCQA":[115,128,148,157,203],"system":[116],"robust.":[117],"Along":[118],"line":[120],"research,":[122],"this":[124],"study,":[125],"an":[126],"audio-aware":[127],"framework":[129,149,158],"proposed.":[131],"Two":[132],"different":[133],"mechanisms":[134],"introduced":[136],"distill":[138],"speech,":[143],"then":[145],"BERT-based":[147],"presented.":[151],"In":[152],"other":[153],"words,":[154],"proposed":[156],"not":[159],"inherits":[161],"advantages":[163],"contextualized":[165],"learned":[168],"BERT":[170],"but":[171],"integrates":[172],"complementary":[174],"information":[176],"distilled":[177],"text-level":[182],"information.":[183],"A":[184],"series":[185],"experiments":[187],"demonstrates":[188],"remarkable":[189],"improvements":[190],"accuracy":[192],"over":[193],"selected":[194],"baselines":[195],"SOTA":[197],"on":[199],"published":[201],"Chinese":[202],"dataset.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}