{"id":"https://openalex.org/W1987238397","doi":"https://doi.org/10.1109/icassp.2013.6638951","title":"Error back propagation for sequence training of Context-Dependent Deep NetworkS for conversational speech transcription","display_name":"Error back propagation for sequence training of Context-Dependent Deep NetworkS for conversational speech transcription","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W1987238397","doi":"https://doi.org/10.1109/icassp.2013.6638951","mag":"1987238397"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6638951","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638951","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100341891","display_name":"Hang Su","orcid":"https://orcid.org/0000-0002-6877-6783"},"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":"Hang Su","raw_affiliation_strings":["Microsoft Research Asia, Beijing, Beijing, CN","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, Beijing, CN","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018012012","display_name":"Gang Li","orcid":"https://orcid.org/0000-0002-8573-1608"},"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":"Gang Li","raw_affiliation_strings":["Microsoft Research, Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"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,Redmond,WA,USA]"],"raw_orcid":null,"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/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, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":145,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6664","last_page":"6668"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10201","display_name":"Speech Recognition and Synthesis","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/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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9947999715805054,"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":0.7549375295639038},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6511037945747375},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6260953545570374},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5851773023605347},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.49057286977767944},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.48964911699295044},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46194085478782654},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3565429449081421},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.10088267922401428},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0820353627204895},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.07509106397628784}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7549375295639038},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6511037945747375},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6260953545570374},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5851773023605347},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.49057286977767944},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.48964911699295044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46194085478782654},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3565429449081421},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.10088267922401428},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0820353627204895},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.07509106397628784},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2013.6638951","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638951","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.368.3342","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.368.3342","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/194345/0006664.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W14913773","https://openalex.org/W34922426","https://openalex.org/W38527073","https://openalex.org/W196761320","https://openalex.org/W217970951","https://openalex.org/W1498436455","https://openalex.org/W1520448186","https://openalex.org/W1989549063","https://openalex.org/W2008353316","https://openalex.org/W2098601596","https://openalex.org/W2114016253","https://openalex.org/W2125234026","https://openalex.org/W2130037349","https://openalex.org/W2136922672","https://openalex.org/W2141778357","https://openalex.org/W2144792281","https://openalex.org/W2147768505","https://openalex.org/W2160306971","https://openalex.org/W2169189000","https://openalex.org/W2296748324","https://openalex.org/W2394932179","https://openalex.org/W2398337534","https://openalex.org/W2403195671","https://openalex.org/W4230820110","https://openalex.org/W4233045210","https://openalex.org/W6601431124","https://openalex.org/W6608133726","https://openalex.org/W6630955860","https://openalex.org/W6682034417","https://openalex.org/W6803034309"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W2028097510","https://openalex.org/W2505877856"],"abstract_inverted_index":{"We":[0],"investigate":[1],"back-propagation":[2],"based":[3],"sequence":[4,17,84],"training":[5,18,95],"of":[6,58,106,122,137],"Context-Dependent":[7],"Deep-Neural-Network":[8],"HMMs,":[9],"or":[10,81],"CD-DNN-HMMs,":[11],"for":[12,110,116],"conversational":[13],"speech":[14],"transcription.":[15],"Theoretically,":[16],"integrates":[19],"with":[20,42,86],"backpropagation":[21],"in":[22],"a":[23,40,101],"straight-forward":[24],"manner.":[25],"However,":[26],"we":[27,70],"find":[28],"that":[29,37],"to":[30,39,50,64,77],"get":[31],"reasonable":[32],"results,":[33],"heuristics":[34],"are":[35,140],"needed":[36],"point":[38],"problem":[41],"lattice":[43],"sparseness:":[44],"The":[45,128],"model":[46],"must":[47],"be":[48],"adjusted":[49],"the":[51,78,83,87,92,97],"updated":[52],"numerator":[53],"lattices":[54],"by":[55],"additional":[56],"iterations":[57],"frame-based":[59,88],"cross-entropy":[60],"(CE)":[61],"training;":[62],"and":[63,114,130],"avoid":[65],"distortions":[66],"from":[67,124],"\u201crunaway\u201d":[68],"models,":[69],"can":[71],"either":[72],"add":[73],"artificial":[74],"silence":[75],"arcs":[76],"denominator":[79],"lattices,":[80],"smooth":[82],"objective":[85,99],"one":[89],"(F-smoothing).":[90],"With":[91,135],"309h":[93],"Switchboard":[94],"set,":[96],"MMI":[98,148],"achieves":[100],"relative":[102],"word-error":[103],"rate":[104],"reduction":[105],"11-15%":[107],"over":[108],"CE":[109,126,144,154],"matched":[111],"test":[112],"sets,":[113],"10-17%":[115],"mismatched":[117],"ones.":[118],"This":[119],"includes":[120],"gains":[121,139],"4-7%":[123],"realigned":[125,143],"iterations.":[127,145],"BMMI":[129],"sMBR":[131],"objectives":[132],"gain":[133],"less.":[134],"2000h":[136],"data,":[138],"2-9%":[141],"after":[142],"Using":[146],"GPGPUs,":[147],"is":[149],"about":[150],"70%":[151],"slower":[152],"than":[153],"training.":[155]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":19},{"year":2016,"cited_by_count":16},{"year":2015,"cited_by_count":19},{"year":2014,"cited_by_count":31},{"year":2013,"cited_by_count":9}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}