{"id":"https://openalex.org/W3016191377","doi":"https://doi.org/10.1109/icassp40776.2020.9053979","title":"Improving Spoken Question Answering Using Contextualized Word Representation","display_name":"Improving Spoken Question Answering Using Contextualized Word Representation","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016191377","doi":"https://doi.org/10.1109/icassp40776.2020.9053979","mag":"3016191377"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5075183307","display_name":"Dan Su","orcid":"https://orcid.org/0000-0001-5746-9545"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Dan Su","raw_affiliation_strings":["Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Clear Water Bay"],"affiliations":[{"raw_affiliation_string":"Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Clear Water Bay","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065856469","display_name":"Pascale Fung","orcid":"https://orcid.org/0000-0002-0628-7132"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Pascale Fung","raw_affiliation_strings":["Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Clear Water Bay"],"affiliations":[{"raw_affiliation_string":"Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Clear Water Bay","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5075183307"],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":1.8558,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.88256578,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"8004","last_page":"8008"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8034621477127075},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.7906482815742493},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6768558621406555},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6424329280853271},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.598276674747467},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5455703735351562},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5104769468307495},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.47651350498199463},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.44078493118286133},{"id":"https://openalex.org/keywords/f1-score","display_name":"F1 score","score":0.4133642911911011},{"id":"https://openalex.org/keywords/reading-comprehension","display_name":"Reading comprehension","score":0.41283342242240906},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.3985408544540405},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1350119709968567}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8034621477127075},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.7906482815742493},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6768558621406555},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6424329280853271},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.598276674747467},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5455703735351562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5104769468307495},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47651350498199463},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.44078493118286133},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.4133642911911011},{"id":"https://openalex.org/C2778780117","wikidata":"https://www.wikidata.org/wiki/Q3269423","display_name":"Reading comprehension","level":3,"score":0.41283342242240906},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.3985408544540405},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1350119709968567},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-102880","is_oa":false,"landing_page_url":"http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=2379-190X&rft.volume=&rft.issue=&rft.date=2020&rft.spage=&rft.aulast=Su&rft.aufirst=Dan&rft.atitle=Improving+Spoken+Question+Answering+Using+Contextualized+Word+Representation&rft.title=2020+IEEE+International+Conference+on+Acoustics%2C+Speech+and+Signal+Processing+Proceedings","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"},{"id":"pmh:oai:repository.ust.hk:1783.1-102880","is_oa":false,"landing_page_url":"http://repository.ust.hk/ir/Record/1783.1-102880","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2407738793","https://openalex.org/W2551396370","https://openalex.org/W2557764419","https://openalex.org/W2609826708","https://openalex.org/W2795497335","https://openalex.org/W2806081754","https://openalex.org/W2885485938","https://openalex.org/W2889787757","https://openalex.org/W2896457183","https://openalex.org/W2912924812","https://openalex.org/W2921273687","https://openalex.org/W2941573484","https://openalex.org/W2962854302","https://openalex.org/W2962904995","https://openalex.org/W2963339397","https://openalex.org/W2963341956","https://openalex.org/W2963446094","https://openalex.org/W2963748441","https://openalex.org/W2963890755","https://openalex.org/W6714009352","https://openalex.org/W6729638187","https://openalex.org/W6729654139","https://openalex.org/W6737119325","https://openalex.org/W6750372648","https://openalex.org/W6752148829","https://openalex.org/W6755207826"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W2387743295","https://openalex.org/W2131833475","https://openalex.org/W2185539916","https://openalex.org/W4221152489"],"abstract_inverted_index":{"While":[0],"question":[1,15],"answering":[2,16],"(QA)":[3],"systems":[4,31],"have":[5,85],"witnessed":[6],"great":[7],"breakthroughs":[8],"in":[9],"reading":[10],"comprehension":[11],"(RC)":[12],"tasks,":[13],"spoken":[14],"(SQA)":[17],"is":[18],"still":[19],"a":[20],"much":[21],"less":[22],"investigated":[23],"area.":[24],"Previous":[25],"work":[26],"shows":[27],"that":[28],"existing":[29,72,137],"SQA":[30,50,99,159],"are":[32],"limited":[33],"by":[34],"catastrophic":[35],"impact":[36],"of":[37,47,66,152],"automatic":[38],"speech":[39],"recognition":[40],"(ASR)":[41],"errors":[42,68],"[1]":[43,118],"and":[44,69,97,120],"the":[45,64,78,94,110,116,127,150],"lack":[46],"large-scale":[48],"real":[49,98,158],"datasets":[51,75],"[2].":[52,130],"In":[53],"this":[54],"paper,":[55],"we":[56,143],"propose":[57],"using":[58,88],"contextualized":[59,89],"word":[60,90],"representations":[61,91],"to":[62,76],"mitigate":[63,77],"effects":[65],"ASR":[67],"pretraining":[70],"on":[71,92,115,126,155],"textual":[73,140],"QA":[74,141],"data":[79,101,129],"scarcity":[80],"issue.":[81],"New":[82],"state-of-the-art":[83],"results":[84],"been":[86],"achieved":[87],"both":[93],"artificially":[95],"synthesised":[96],"benchmark":[100],"sets,":[102],"with":[103,136],"21.5":[104],"EM/18.96":[105],"F1":[106,123,147],"score":[107,124],"improvement":[108,125,148],"over":[109,149],"sub-word":[111],"unit":[112],"based":[113],"baseline":[114,151],"Spoken-SQuAD":[117],"data,":[119,142],"13.11":[121],"EM/10.99":[122],"ODSQA":[128],"By":[131],"further":[132],"fine-tuning":[133],"pre-trained":[134],"models":[135],"large":[138],"scaled":[139],"obtained":[144],"38.12":[145],"EM/34.1":[146],"fine-tuned":[153],"only":[154],"small":[156],"sized":[157],"data.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}