{"id":"https://openalex.org/W2046588080","doi":"https://doi.org/10.1109/slt.2012.6424212","title":"Context-dependent Deep Neural Networks for audio indexing of real-life data","display_name":"Context-dependent Deep Neural Networks for audio indexing of real-life data","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W2046588080","doi":"https://doi.org/10.1109/slt.2012.6424212","mag":"2046588080"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2012.6424212","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2012.6424212","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Spoken Language Technology Workshop (SLT)","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/A5100438769","display_name":"Gang Li","orcid":"https://orcid.org/0000-0003-1583-641X"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Gang Li","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft Research Asia,"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia,","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024568191","display_name":"Huifeng Zhu","orcid":"https://orcid.org/0000-0002-0099-1911"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huifeng Zhu","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft Research Asia,"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia,","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101696752","display_name":"Cheng Gong","orcid":"https://orcid.org/0000-0002-2135-4997"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gong Cheng","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft Research Asia,"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia,","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109226002","display_name":"Kit Thambiratnam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kit Thambiratnam","raw_affiliation_strings":["Microsoft Search Technology Center, Beijing, China","Microsoft Search Technology Center, 5 Danling Street, Haidian District, Beijing 100080, P.R.C"],"affiliations":[{"raw_affiliation_string":"Microsoft Search Technology Center, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Microsoft Search Technology Center, 5 Danling Street, Haidian District, Beijing 100080, P.R.C","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057801896","display_name":"Behrooz Chitsaz","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":"Behrooz Chitsaz","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","Microsoft Research, One Microsoft Way, Redmond, WA, 98052 USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research, One Microsoft Way, Redmond, WA, 98052 USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"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":"Dong Yu","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","Microsoft Research, One Microsoft Way, Redmond, WA, 98052 USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research, One Microsoft Way, Redmond, WA, 98052 USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072932051","display_name":"Frank Seide","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Frank Seide","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft Research Asia,"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia,","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100438769"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":1.2386,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.82645777,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"143","last_page":"148"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8311660289764404},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8280447125434875},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7123767733573914},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6661040782928467},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5776540637016296},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5650704503059387},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.559768795967102},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5492444634437561},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5378486514091492},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4722955524921417},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42500734329223633},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3671340346336365}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8311660289764404},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8280447125434875},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7123767733573914},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6661040782928467},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5776540637016296},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5650704503059387},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.559768795967102},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5492444634437561},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5378486514091492},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4722955524921417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42500734329223633},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3671340346336365},{"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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:10.1109/slt.2012.6424212","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2012.6424212","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.368.5057","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.368.5057","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/194342/0000143.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W44815768","https://openalex.org/W217970951","https://openalex.org/W1218987319","https://openalex.org/W1498436455","https://openalex.org/W1520448186","https://openalex.org/W2008353316","https://openalex.org/W2035573568","https://openalex.org/W2093794678","https://openalex.org/W2112477549","https://openalex.org/W2114016253","https://openalex.org/W2123861623","https://openalex.org/W2136922672","https://openalex.org/W2144792281","https://openalex.org/W2147768505","https://openalex.org/W2160306971","https://openalex.org/W2167556823","https://openalex.org/W2169189000","https://openalex.org/W2394932179","https://openalex.org/W4233045210","https://openalex.org/W6601785968","https://openalex.org/W6630955860","https://openalex.org/W6682034417","https://openalex.org/W6684666846","https://openalex.org/W6803034309"],"related_works":["https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W2153098279","https://openalex.org/W2160650576","https://openalex.org/W2061937230","https://openalex.org/W4245698648","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290"],"abstract_inverted_index":{"We":[0,78],"apply":[1],"Context-Dependent":[2],"Deep-Neural-Network":[3],"HMMs,":[4,54],"or":[5],"CD-DNN-HMMs,":[6],"to":[7,50,100,109],"the":[8,25,40,59,94,114,140,162],"real-life":[9,73],"problem":[10],"of":[11,14,31,92,137,157],"audio":[12,76],"indexing":[13],"data":[15,103],"across":[16],"various":[17],"sources.":[18],"Recently,":[19],"we":[20,127],"had":[21],"shown":[22],"that":[23,80,129,143],"on":[24,28,90],"Switchboard":[26],"benchmark":[27],"speaker-independent":[29,84],"transcription":[30],"phone":[32],"calls,":[33],"CD-DNN-HMMs":[34],"with":[35,86],"7":[36],"hidden":[37],"layers":[38],"reduce":[39],"word":[41],"error":[42],"rate":[43],"by":[44,56,165,169],"as":[45,47],"much":[46],"one-third,":[48],"compared":[49],"discriminatively":[51],"trained":[52,89],"Gaussian-mixture":[53],"and":[55,106,142],"one-fourth":[57,95],"if":[58],"GMM-HMM":[60],"also":[61],"uses":[62],"fMPE":[63],"features.":[64],"This":[65],"paper":[66],"takes":[67],"CD-DNN-HMM":[68],"based":[69],"recognition":[70],"into":[71],"a":[72,110,134,148,172],"deployment":[74],"for":[75,81],"indexing.":[77],"find":[79,128],"our":[82,154],"best":[83],"CD-DNN-HMM,":[85],"32k":[87],"senones":[88,138],"2000h":[91],"data,":[93],"reduction":[96],"does":[97],"carry":[98],"over":[99],"inhomogeneous":[101],"field":[102],"(video":[104],"podcasts":[105],"talks).":[107],"Compared":[108],"speaker-adaptive":[111],"GMM":[112],"system,":[113],"relative":[115,174],"improvement":[116],"is":[117,147],"18%,":[118],"at":[119,171],"very":[120],"similar":[121],"end-to-end":[122],"runtime.":[123],"In":[124],"system":[125],"building,":[126],"DNNs":[130],"can":[131],"benefit":[132],"from":[133],"larger":[135],"number":[136],"than":[139],"GMM-HMM;":[141],"DNN":[144],"likelihood":[145],"evaluation":[146],"sizeable":[149],"runtime":[150,168],"factor":[151],"even":[152],"in":[153],"wide-beam":[155],"context":[156],"generating":[158],"rich":[159],"lattices:":[160],"Cutting":[161],"model":[163],"size":[164],"60%":[166],"reduces":[167],"one-third":[170],"5%":[173],"WER":[175],"loss.":[176]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}