{"id":"https://openalex.org/W14656806","doi":"https://doi.org/10.21437/interspeech.2012-324","title":"Joint decoding for speech recognition and semantic tagging","display_name":"Joint decoding for speech recognition and semantic tagging","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W14656806","doi":"https://doi.org/10.21437/interspeech.2012-324","mag":"14656806"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-324","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-324","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","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/A5000621526","display_name":"Anoop Deoras","orcid":"https://orcid.org/0009-0007-4566-8767"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Anoop Deoras","raw_affiliation_strings":["Microsoft (United States), Redmond, United States"],"affiliations":[{"raw_affiliation_string":"Microsoft (United States), Redmond, United States","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072875068","display_name":"Ruhi Sarikaya","orcid":"https://orcid.org/0000-0003-2676-2831"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruhi Sarikaya","raw_affiliation_strings":["Microsoft (United States), Redmond, United States"],"affiliations":[{"raw_affiliation_string":"Microsoft (United States), Redmond, United States","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087941479","display_name":"G\u00f6khan T\u00fcr","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gokhan Tur","raw_affiliation_strings":["Microsoft (United States), Redmond, United States"],"affiliations":[{"raw_affiliation_string":"Microsoft (United States), Redmond, United States","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068709817","display_name":"Dilek Hakkani\u2010T\u00fcr","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dilek Hakkani-T\u00fcr","raw_affiliation_strings":["Microsoft (United States), Redmond, United States"],"affiliations":[{"raw_affiliation_string":"Microsoft (United States), Redmond, United States","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5000621526"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":5.7476,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.95694795,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1067","last_page":"1070"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9994000196456909,"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":0.8635438680648804},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7353336811065674},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6093285083770752},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.606146514415741},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5989164113998413},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5841500163078308},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5202797055244446},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5042902231216431},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5010044574737549},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4790112376213074},{"id":"https://openalex.org/keywords/cascade","display_name":"Cascade","score":0.46578067541122437},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.4425268769264221},{"id":"https://openalex.org/keywords/interpreter","display_name":"Interpreter","score":0.43558380007743835},{"id":"https://openalex.org/keywords/joint-probability-distribution","display_name":"Joint probability distribution","score":0.41970115900039673},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41768592596054077},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4148298501968384},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.4130808115005493},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.17714235186576843},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16910415887832642},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.11338844895362854}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8635438680648804},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7353336811065674},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6093285083770752},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.606146514415741},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5989164113998413},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5841500163078308},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5202797055244446},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5042902231216431},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5010044574737549},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4790112376213074},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.46578067541122437},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.4425268769264221},{"id":"https://openalex.org/C122783720","wikidata":"https://www.wikidata.org/wiki/Q183065","display_name":"Interpreter","level":2,"score":0.43558380007743835},{"id":"https://openalex.org/C18653775","wikidata":"https://www.wikidata.org/wiki/Q1333358","display_name":"Joint probability distribution","level":2,"score":0.41970115900039673},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41768592596054077},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4148298501968384},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.4130808115005493},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17714235186576843},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16910415887832642},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.11338844895362854},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2012-324","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-324","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.261.853","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.261.853","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.clsp.jhu.edu/%7Eadeoras/HomePage/Anoop_Deoras_files/InterSpeech-2012.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W169943709","https://openalex.org/W1582482241","https://openalex.org/W1768132882","https://openalex.org/W2007080341","https://openalex.org/W2007261869","https://openalex.org/W2142904027","https://openalex.org/W2147880316","https://openalex.org/W2149980590","https://openalex.org/W2150859660","https://openalex.org/W2158873310","https://openalex.org/W2160986985"],"related_works":["https://openalex.org/W2980207396","https://openalex.org/W3156493709","https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W2129812225","https://openalex.org/W4290708361","https://openalex.org/W2523799048","https://openalex.org/W2155620340"],"abstract_inverted_index":{"Most":[0],"conversational":[1,65],"understanding":[2,24,66],"(CU)":[3],"systems":[4,35],"today":[5],"employ":[6],"a":[7,56,81,91,143,155],"cascade":[8,146],"approach,":[9],"where":[10],"the":[11,60,64,76,99,111,150],"best":[12,28],"hypothesis":[13,29],"from":[14,46],"automatic":[15],"speech":[16],"recognizer":[17,152],"(ASR)":[18],"is":[19,30,70],"fed":[20,32],"into":[21,33,52],"spoken":[22],"language":[23],"(SLU)":[25],"module,":[26],"whose":[27],"then":[31],"other":[34],"such":[36,43],"as":[37,102,104],"interpreter":[38],"or":[39],"dialog":[40],"manager.":[41],"In":[42],"approaches,":[44],"errors":[45],"one":[47],"statistical":[48,77],"module":[49,54],"irreversibly":[50],"propagates":[51],"another":[53],"causing":[55],"serious":[57],"degradation":[58],"in":[59,86,95,125,134],"overall":[61],"performance":[62],"of":[63,149],"system.":[67],"Thus":[68],"it":[69],"desirable":[71],"to":[72,142],"jointly":[73,109],"optimize":[74],"all":[75],"modules":[78],"together.":[79],"As":[80],"first":[82],"step":[83],"towards":[84],"this,":[85],"this":[87],"paper,":[88],"we":[89,97,119],"propose":[90],"joint":[92],"decoding":[93],"framework":[94],"which":[96],"predict":[98],"optimal":[100],"word":[101,126],"well":[103],"slot":[105,138,156],"(semantic":[106],"tag)":[107],"sequence":[108,157],"given":[110],"input":[112],"acoustic":[113],"stream.":[114],"On":[115],"Microsoft\u2019s":[116],"CU":[117],"system,":[118],"show":[120],"1.3":[121],"%":[122],"absolute":[123,132],"reduction":[124],"error":[127],"rate":[128],"(WER)":[129],"and":[130],"1.2%":[131],"improvement":[133],"F":[135],"measure":[136],"for":[137],"prediction":[139],"when":[140],"compared":[141],"very":[144],"strong":[145],"baseline":[147],"comprising":[148],"state-of-the-art":[151],"followed":[153],"by":[154],"tagger.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}