{"id":"https://openalex.org/W2084339293","doi":"https://doi.org/10.1109/jproc.2012.2236631","title":"Speech-Centric Information Processing: An Optimization-Oriented Approach","display_name":"Speech-Centric Information Processing: An Optimization-Oriented Approach","publication_year":2013,"publication_date":"2013-04-17","ids":{"openalex":"https://openalex.org/W2084339293","doi":"https://doi.org/10.1109/jproc.2012.2236631","mag":"2084339293"},"language":"en","primary_location":{"id":"doi:10.1109/jproc.2012.2236631","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jproc.2012.2236631","pdf_url":"https://ieeexplore.ieee.org/ielx7/5/6504474/06472007.pdf","source":{"id":"https://openalex.org/S68686220","display_name":"Proceedings of the IEEE","issn_l":"0018-9219","issn":["0018-9219","1558-2256"],"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":"Proceedings of the IEEE","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://ieeexplore.ieee.org/ielx7/5/6504474/06472007.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101727205","display_name":"Xiaodong He","orcid":"https://orcid.org/0000-0002-9463-9168"},"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":"Xiaodong He","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","[Microsoft Research,Redmond,WA,USA]"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"[Microsoft Research,Redmond,WA,USA]","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100671324","display_name":"Li Deng","orcid":"https://orcid.org/0000-0002-1014-0790"},"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":"Li Deng","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","[Microsoft Research,Redmond,WA,USA]"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"[Microsoft Research,Redmond,WA,USA]","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101727205"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":10.8732,"has_fulltext":true,"cited_by_count":44,"citation_normalized_percentile":{"value":0.98182434,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"101","issue":"5","first_page":"1116","last_page":"1135"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T12031","display_name":"Speech and dialogue systems","score":0.9991999864578247,"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":0.8493993282318115},{"id":"https://openalex.org/keywords/interfacing","display_name":"Interfacing","score":0.7629484534263611},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.6724961996078491},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.5882059931755066},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5556883811950684},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.540318489074707},{"id":"https://openalex.org/keywords/speech-analytics","display_name":"Speech analytics","score":0.5139631628990173},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49830007553100586},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.49060383439064026},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4850437045097351},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4688355028629303},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4445212185382843},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4371185004711151},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.416746586561203},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33830124139785767},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.312896728515625}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8493993282318115},{"id":"https://openalex.org/C2776303644","wikidata":"https://www.wikidata.org/wiki/Q1020499","display_name":"Interfacing","level":2,"score":0.7629484534263611},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.6724961996078491},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.5882059931755066},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5556883811950684},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.540318489074707},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.5139631628990173},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49830007553100586},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.49060383439064026},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4850437045097351},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4688355028629303},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4445212185382843},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4371185004711151},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.416746586561203},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33830124139785767},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.312896728515625},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/jproc.2012.2236631","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jproc.2012.2236631","pdf_url":"https://ieeexplore.ieee.org/ielx7/5/6504474/06472007.pdf","source":{"id":"https://openalex.org/S68686220","display_name":"Proceedings of the IEEE","issn_l":"0018-9219","issn":["0018-9219","1558-2256"],"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":"Proceedings of the IEEE","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.303.4845","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.303.4845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/pubs/179540/ProcIEEE_He_deng_finalsub.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1109/jproc.2012.2236631","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jproc.2012.2236631","pdf_url":"https://ieeexplore.ieee.org/ielx7/5/6504474/06472007.pdf","source":{"id":"https://openalex.org/S68686220","display_name":"Proceedings of the IEEE","issn_l":"0018-9219","issn":["0018-9219","1558-2256"],"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":"Proceedings of the IEEE","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7400000095367432,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2084339293.pdf","grobid_xml":"https://content.openalex.org/works/W2084339293.grobid-xml"},"referenced_works_count":132,"referenced_works":["https://openalex.org/W1410460","https://openalex.org/W16552454","https://openalex.org/W21273448","https://openalex.org/W73748647","https://openalex.org/W84880661","https://openalex.org/W89495765","https://openalex.org/W109381481","https://openalex.org/W207489108","https://openalex.org/W233551787","https://openalex.org/W245306944","https://openalex.org/W648947103","https://openalex.org/W1269046860","https://openalex.org/W1485908763","https://openalex.org/W1500419248","https://openalex.org/W1506371579","https://openalex.org/W1512542822","https://openalex.org/W1541007220","https://openalex.org/W1574530145","https://openalex.org/W1579838312","https://openalex.org/W1649407914","https://openalex.org/W1663973292","https://openalex.org/W1786620475","https://openalex.org/W1975244201","https://openalex.org/W1985554184","https://openalex.org/W1989168222","https://openalex.org/W1992306964","https://openalex.org/W1998262686","https://openalex.org/W2002890640","https://openalex.org/W2006544565","https://openalex.org/W2006969979","https://openalex.org/W2008652694","https://openalex.org/W2008884998","https://openalex.org/W2013438303","https://openalex.org/W2021396747","https://openalex.org/W2024277778","https://openalex.org/W2024539680","https://openalex.org/W2025040932","https://openalex.org/W2029223910","https://openalex.org/W2032005922","https://openalex.org/W2040249897","https://openalex.org/W2049167423","https://openalex.org/W2050552609","https://openalex.org/W2067132423","https://openalex.org/W2068484625","https://openalex.org/W2074818733","https://openalex.org/W2077574412","https://openalex.org/W2078950386","https://openalex.org/W2080998092","https://openalex.org/W2084514013","https://openalex.org/W2093866254","https://openalex.org/W2095734449","https://openalex.org/W2096389830","https://openalex.org/W2096557251","https://openalex.org/W2098601596","https://openalex.org/W2100966557","https://openalex.org/W2101105183","https://openalex.org/W2106347453","https://openalex.org/W2112771660","https://openalex.org/W2113106066","https://openalex.org/W2114483840","https://openalex.org/W2114863652","https://openalex.org/W2116053234","https://openalex.org/W2117109565","https://openalex.org/W2118329604","https://openalex.org/W2120375264","https://openalex.org/W2122511433","https://openalex.org/W2124173482","https://openalex.org/W2125200094","https://openalex.org/W2126033156","https://openalex.org/W2128854142","https://openalex.org/W2129141326","https://openalex.org/W2129989249","https://openalex.org/W2130839206","https://openalex.org/W2132187905","https://openalex.org/W2132283655","https://openalex.org/W2136530135","https://openalex.org/W2136545725","https://openalex.org/W2136727248","https://openalex.org/W2137862343","https://openalex.org/W2139113820","https://openalex.org/W2139647714","https://openalex.org/W2140343992","https://openalex.org/W2143564602","https://openalex.org/W2143908786","https://openalex.org/W2144663079","https://openalex.org/W2146574666","https://openalex.org/W2147768505","https://openalex.org/W2148702268","https://openalex.org/W2148986421","https://openalex.org/W2149120305","https://openalex.org/W2149980590","https://openalex.org/W2150622104","https://openalex.org/W2150859660","https://openalex.org/W2151742940","https://openalex.org/W2153653739","https://openalex.org/W2153962611","https://openalex.org/W2156163116","https://openalex.org/W2157041970","https://openalex.org/W2158808283","https://openalex.org/W2160815625","https://openalex.org/W2162432783","https://openalex.org/W2163552996","https://openalex.org/W2163937804","https://openalex.org/W2166799778","https://openalex.org/W2166947141","https://openalex.org/W2168262690","https://openalex.org/W2169434751","https://openalex.org/W2170955770","https://openalex.org/W2184045248","https://openalex.org/W2188958590","https://openalex.org/W2294759826","https://openalex.org/W2395992401","https://openalex.org/W2408327647","https://openalex.org/W2505072414","https://openalex.org/W2917604489","https://openalex.org/W4212863985","https://openalex.org/W4251560691","https://openalex.org/W4285719527","https://openalex.org/W6603041686","https://openalex.org/W6603374476","https://openalex.org/W6652311901","https://openalex.org/W6674565674","https://openalex.org/W6674743151","https://openalex.org/W6678800364","https://openalex.org/W6679228711","https://openalex.org/W6679755471","https://openalex.org/W6681365651","https://openalex.org/W6683422677","https://openalex.org/W6683959349","https://openalex.org/W6685119187","https://openalex.org/W6697079997","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2003020325","https://openalex.org/W2164499211","https://openalex.org/W4389400962","https://openalex.org/W2024407979","https://openalex.org/W134179020","https://openalex.org/W2909367404","https://openalex.org/W2184127972","https://openalex.org/W2794066735","https://openalex.org/W2525874696","https://openalex.org/W1965739709"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,129],"recognition":[2,130],"(ASR)":[3],"is":[4,90,133],"a":[5],"central":[6],"and":[7,33,47,54,86,96,111,136,146,154,160],"common":[8],"component":[9],"of":[10,44,59,114,143],"voice-driven":[11],"information":[12,48,117],"processing":[13,42,118],"systems":[14],"in":[15,56,81,107,124,128,149],"human":[16],"language":[17,21,25],"technology,":[18],"including":[19],"spoken":[20,24,30],"translation":[22],"(SLT),":[23],"understanding":[26],"(SLU),":[27],"voice":[28],"search,":[29],"document":[31],"retrieval,":[32],"so":[34],"on.":[35],"Interfacing":[36],"ASR":[37],"with":[38],"its":[39],"downstream":[40],"text-based":[41],"tasks":[43],"translation,":[45],"understanding,":[46],"retrieval":[49],"(IR)":[50],"creates":[51],"both":[52,108],"challenges":[53,153],"opportunities":[55,156],"optimal":[57],"design":[58,74,88,121],"the":[60,71,76,79,93,97,109,115,126,144],"combined,":[61],"speech-enabled":[62],"systems.":[63],"We":[64],"present":[65],"an":[66,141],"optimization-oriented":[67],"statistical":[68],"framework":[69],"for":[70,103],"overall":[72],"system":[73,99,120],"where":[75,87],"interactions":[77],"between":[78,92],"subsystems":[80],"tandem":[82],"are":[83,122,157],"fully":[84,134],"incorporated":[85],"consistency":[89],"established":[91],"optimization":[94],"objectives":[95,106],"end-to-end":[98],"performance":[100],"metrics.":[101],"Techniques":[102],"optimizing":[104],"such":[105],"decoding":[110],"learning":[112],"phases":[113],"speech-centric":[116],"(SCIP)":[119],"described,":[123],"which":[125],"uncertainty":[127],"subsystem's":[131],"outputs":[132],"considered":[135],"marginalized.":[137],"This":[138],"paper":[139],"provides":[140],"overview":[142],"past":[145],"current":[147],"work":[148],"this":[150],"area.":[151],"Future":[152],"new":[155],"also":[158],"discussed":[159],"analyzed.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}