{"id":"https://openalex.org/W2019973879","doi":"https://doi.org/10.1109/icassp.2014.6854674","title":"Standalone training of context-dependent deep neural network acoustic models","display_name":"Standalone training of context-dependent deep neural network acoustic models","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2019973879","doi":"https://doi.org/10.1109/icassp.2014.6854674","mag":"2019973879"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854674","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854674","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5007989522","display_name":"C. Zhang","orcid":"https://orcid.org/0000-0002-2173-6872"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"C. Zhang","raw_affiliation_strings":["Engineering Dept, Cambridge University, Cambridge, U.K","Engineering Department, Cambridge University, Cambridge, UK,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering Dept, Cambridge University, Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Engineering Department, Cambridge University, Cambridge, UK,","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076432109","display_name":"P. C. Woodland","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"P. C. Woodland","raw_affiliation_strings":["Engineering Dept, Cambridge University, Cambridge, U.K","Engineering Department, Cambridge University, Cambridge, UK,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering Dept, Cambridge University, Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Engineering Department, Cambridge University, Cambridge, UK,","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"5597","last_page":"5601"},"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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.9190462827682495},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7656975984573364},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6844174861907959},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6107420921325684},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6080130338668823},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5882145166397095},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5361354947090149},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5219727754592896},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5208602547645569},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.48988598585128784},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48562827706336975},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4833504855632782},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4194054901599884},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4100748300552368},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.23125138878822327},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09446796774864197},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.07857531309127808}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.9190462827682495},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7656975984573364},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6844174861907959},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6107420921325684},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6080130338668823},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5882145166397095},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5361354947090149},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5219727754592896},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5208602547645569},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.48988598585128784},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48562827706336975},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4833504855632782},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4194054901599884},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4100748300552368},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.23125138878822327},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09446796774864197},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.07857531309127808},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2014.6854674","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854674","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:generic.eprints.org:646790","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/646790/","pdf_url":null,"source":{"id":"https://openalex.org/S4406922847","display_name":"Cambridge University Engineering Department Publications Database","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.8199999928474426,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G4055593462","display_name":null,"funder_award_id":"EP/I031022/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1553004968","https://openalex.org/W1554663460","https://openalex.org/W1992912377","https://openalex.org/W1993660824","https://openalex.org/W2062164080","https://openalex.org/W2113094193","https://openalex.org/W2118716571","https://openalex.org/W2122028591","https://openalex.org/W2147768505","https://openalex.org/W2150907703","https://openalex.org/W2154423186","https://openalex.org/W2158069733","https://openalex.org/W2160306971","https://openalex.org/W2166993553","https://openalex.org/W2172130635","https://openalex.org/W2184045248","https://openalex.org/W2394932179","https://openalex.org/W2411442511","https://openalex.org/W4300402905","https://openalex.org/W4388297464","https://openalex.org/W6648822320","https://openalex.org/W6682398751","https://openalex.org/W6686210252"],"related_works":["https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W2160650576","https://openalex.org/W4245698648","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306","https://openalex.org/W2944691285"],"abstract_inverted_index":{"Recently,":[0],"context-dependent":[1],"(CD)":[2],"deep":[3],"neural":[4],"network":[5],"(DNN)":[6],"hidden":[7],"Markov":[8],"models":[9,17,28],"(HMMs)":[10],"have":[11,100],"been":[12,101],"widely":[13],"used":[14],"as":[15],"acoustic":[16],"for":[18,52],"speech":[19],"recognition.":[20],"However,":[21],"the":[22,81,86,92,104,110],"standard":[23],"method":[24,51],"to":[25,119],"build":[26,69],"such":[27,59],"requires":[29],"target":[30],"training":[31,53],"labels":[32],"from":[33],"a":[34,50,60,70],"system":[35,112],"using":[36,91],"HMMs":[37],"with":[38,75],"Gaussian":[39],"mixture":[40],"model":[41],"output":[42,83],"distributions":[43,84],"(GMM-HMMs).":[44],"In":[45],"this":[46,65],"paper,":[47],"we":[48],"introduce":[49],"state-of-the-art":[54],"CD-DNN-HMMs":[55],"without":[56],"relying":[57],"on":[58,103,123],"pre-existing":[61],"system.":[62],"We":[63],"achieve":[64],"in":[66],"two":[67],"steps:":[68],"context-independent":[71],"(CI)":[72],"DNN":[73],"iteratively":[74],"word":[76,115],"transcriptions,":[77],"and":[78,109,126],"then":[79],"cluster":[80],"equivalent":[82],"of":[85],"untied":[87],"CD-DNN":[88],"HMM":[89],"states":[90],"decision":[93],"tree":[94],"based":[95,122],"state":[96],"tying":[97],"approach.":[98],"Experiments":[99],"performed":[102],"Wall":[105],"Street":[106],"Journal":[107],"corpus":[108],"resulting":[111],"gave":[113],"comparable":[114],"error":[116],"rates":[117],"(WER)":[118],"CD-DNNs":[120],"built":[121],"GMM-HMM":[124],"alignments":[125],"state-clustering.":[127]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}