{"id":"https://openalex.org/W2936979094","doi":"https://doi.org/10.1109/icassp.2019.8683749","title":"Using Deep-Q Network to Select Candidates from N-best Speech Recognition Hypotheses for Enhancing Dialogue State Tracking","display_name":"Using Deep-Q Network to Select Candidates from N-best Speech Recognition Hypotheses for Enhancing Dialogue State Tracking","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2936979094","doi":"https://doi.org/10.1109/icassp.2019.8683749","mag":"2936979094"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683749","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683749","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/A5030771512","display_name":"Richard Tzong\u2010Han Tsai","orcid":"https://orcid.org/0000-0003-0513-107X"},"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":"Richard Tzong-Han Tsai","raw_affiliation_strings":["NTU IoX Center, National Taiwan University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTU IoX Center, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061592046","display_name":"Chia\u2010Hao Chen","orcid":"https://orcid.org/0000-0003-1311-8342"},"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":"Chia-Hao Chen","raw_affiliation_strings":["NTU IoX Center, National Taiwan University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTU IoX Center, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110439145","display_name":"Chun-Kai Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chun-Kai Wu","raw_affiliation_strings":["Department of Computer Science, National Tsing Hua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Tsing Hua University","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084645089","display_name":"Yu\u2010Cheng Hsiao","orcid":"https://orcid.org/0000-0003-3312-7318"},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Cheng Hsiao","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Central University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Central University","institution_ids":["https://openalex.org/I22265921"]}]},{"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":["NTU IoX Center, National Taiwan University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTU IoX Center, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1446,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.55733374,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"7","issue":null,"first_page":"7375","last_page":"7379"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":1.0,"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/T12031","display_name":"Speech and dialogue systems","score":1.0,"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":0.9973000288009644,"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":0.9968000054359436,"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":0.8416891098022461},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6505602598190308},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5760289430618286},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5090834498405457},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4901643693447113},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.4832799732685089},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.478086918592453},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.42254698276519775},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.41563478112220764},{"id":"https://openalex.org/keywords/dilemma","display_name":"Dilemma","score":0.41000980138778687},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32152366638183594},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09198310971260071}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8416891098022461},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6505602598190308},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5760289430618286},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5090834498405457},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4901643693447113},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.4832799732685089},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.478086918592453},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.42254698276519775},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.41563478112220764},{"id":"https://openalex.org/C2778496695","wikidata":"https://www.wikidata.org/wiki/Q254128","display_name":"Dilemma","level":2,"score":0.41000980138778687},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32152366638183594},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09198310971260071},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683749","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683749","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5099999904632568}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320719","display_name":"Department of Science and Technology, Ministry of Science and Technology, India","ror":"https://ror.org/0101xrq71"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1491973539","https://openalex.org/W1502662603","https://openalex.org/W1509171145","https://openalex.org/W1757796397","https://openalex.org/W1785674045","https://openalex.org/W1986362700","https://openalex.org/W1996957559","https://openalex.org/W2064675550","https://openalex.org/W2108806737","https://openalex.org/W2114537044","https://openalex.org/W2127107099","https://openalex.org/W2129405869","https://openalex.org/W2145339207","https://openalex.org/W2468710617","https://openalex.org/W2473839124","https://openalex.org/W2493916176","https://openalex.org/W2560678344","https://openalex.org/W2949905447","https://openalex.org/W2963797754","https://openalex.org/W3011120880","https://openalex.org/W3139377883","https://openalex.org/W4298857966","https://openalex.org/W4301083246","https://openalex.org/W6629490593","https://openalex.org/W6629890113","https://openalex.org/W6637967152","https://openalex.org/W6638115398","https://openalex.org/W6676271009","https://openalex.org/W6723250868","https://openalex.org/W6775686901"],"related_works":["https://openalex.org/W2374250903","https://openalex.org/W2350209916","https://openalex.org/W2475524763","https://openalex.org/W2363851383","https://openalex.org/W4386907265","https://openalex.org/W2058752985","https://openalex.org/W2293740626","https://openalex.org/W2763412546","https://openalex.org/W1499712254","https://openalex.org/W2915347927"],"abstract_inverted_index":{"Most":[0],"state-of-the-art":[1],"dialogue":[2,9,54,158],"state":[3,10],"tracking":[4],"(DST)":[5],"methods":[6],"infer":[7],"the":[8,31,40,53,70,90,125,142,148,157,161,180],"based":[11,134],"on":[12,135],"ground-truth":[13],"transcriptions":[14,34,73,133],"of":[15,85],"utterances.":[16],"In":[17,36,114],"real-world":[18],"situations,":[19],"utterances":[20],"are":[21],"transcribed":[22],"by":[23,152,174],"automatic":[24],"speech":[25],"recognition":[26],"(ASR)":[27],"systems,":[28],"which":[29,78,145,176],"output":[30],"n-best":[32],"candidate":[33,72],"(hypotheses).":[35],"certain":[37],"noisy":[38],"environments,":[39],"best":[41],"transcription":[42],"is":[43,177,193],"often":[44,66],"imperfect,":[45],"severely":[46],"influencing":[47],"DST":[48,172],"accuracy":[49,84,173],"and":[50],"possibly":[51],"causing":[52],"system":[55],"to":[56,76,82,122,128,195],"stall":[57],"or":[58,62],"loop.":[59],"The":[60],"missed":[61],"misrecognized":[63],"words":[64],"can":[65,170],"be":[67,80],"found":[68],"in":[69],"runner-up":[71,131],"from":[74],"2":[75],"n,":[77],"could":[79],"used":[81],"improve":[83,171],"DST.":[86],"However,":[87],"looking":[88],"beyond":[89],"top-ranked":[91],"ASR":[92,132,150,198],"results":[93,199],"poses":[94],"a":[95,119],"dilemma:":[96],"going":[97,105],"too":[98],"far":[99,106],"may":[100,108],"introduce":[101],"noise,":[102],"while":[103],"not":[104,109],"enough":[107],"uncover":[110],"any":[111,201],"useful":[112],"information.":[113],"this":[115],"paper,":[116],"we":[117,155],"propose":[118],"novel":[120],"approach":[121],"automatically":[123],"determine":[124],"optimal":[126],"time":[127],"stop":[129],"reexamining":[130],"deep":[136],"reinforcement":[137],"learning.":[138],"Our":[139],"method":[140,169,192],"outperforms":[141],"baseline":[143],"system,":[144],"uses":[146],"only":[147],"top-1":[149],"result,":[151],"3.1%.":[153],"Then,":[154],"select":[156,196],"rounds":[159],"with":[160],"top-10":[162],"largest":[163],"word":[164],"error":[165],"rate":[166,183],"(WER),":[167],"our":[168,190],"15.4%,":[175],"five":[178],"times":[179],"overall":[181],"improvement":[182,186],"(3.1%).":[184],"This":[185],"was":[187],"expected":[188],"because":[189],"proposed":[191],"able":[194],"informative":[197],"at":[200],"rank.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}