{"id":"https://openalex.org/W2550928100","doi":"https://doi.org/10.1109/taslp.2016.2630305","title":"Multitask Learning of Context-Dependent Targets in Deep Neural Network Acoustic Models","display_name":"Multitask Learning of Context-Dependent Targets in Deep Neural Network Acoustic Models","publication_year":2016,"publication_date":"2016-11-17","ids":{"openalex":"https://openalex.org/W2550928100","doi":"https://doi.org/10.1109/taslp.2016.2630305","mag":"2550928100"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2016.2630305","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2630305","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/2dc0d0ba-e4d4-44b6-b8bc-1c51fce24643","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102911387","display_name":"Peter Bell","orcid":"https://orcid.org/0000-0002-9597-9615"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peter Bell","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, U.K","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084169592","display_name":"Pawe\u0142 \u015awi\u0119toja\u0144ski","orcid":"https://orcid.org/0000-0001-5896-4505"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pawel Swietojanski","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, U.K","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027442277","display_name":"Steve Renals","orcid":"https://orcid.org/0000-0002-8790-3389"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Steve Renals","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, U.K","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":3.8979,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.94451746,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"25","issue":"2","first_page":"238","last_page":"247"},"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":0.9997000098228455,"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":0.9995999932289124,"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":0.7816932797431946},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6734647750854492},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5922670960426331},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.5189575552940369},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5166759490966797},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5150918364524841},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.49662667512893677},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.48024633526802063},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.471128910779953},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4622478485107422},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4570910334587097},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.410852313041687}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7816932797431946},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6734647750854492},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5922670960426331},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.5189575552940369},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5166759490966797},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5150918364524841},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.49662667512893677},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.48024633526802063},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.471128910779953},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4622478485107422},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4570910334587097},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.410852313041687},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2016.2630305","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2630305","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/2dc0d0ba-e4d4-44b6-b8bc-1c51fce24643","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/2dc0d0ba-e4d4-44b6-b8bc-1c51fce24643","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bell, P, Swietojanski, P & Renals, S 2017, 'Multitask Learning of Context-Dependent Targets in Deep Neural Network Acoustic Models', IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 25, no. 2, pp. 238 - 247. https://doi.org/10.1109/TASLP.2016.2630305","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/2dc0d0ba-e4d4-44b6-b8bc-1c51fce24643","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/2dc0d0ba-e4d4-44b6-b8bc-1c51fce24643","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bell, P, Swietojanski, P & Renals, S 2017, 'Multitask Learning of Context-Dependent Targets in Deep Neural Network Acoustic Models', IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 25, no. 2, pp. 238 - 247. https://doi.org/10.1109/TASLP.2016.2630305","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G3790594077","display_name":"Natural Speech Technology","funder_award_id":"EP/I031022/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W129870797","https://openalex.org/W161810042","https://openalex.org/W173856587","https://openalex.org/W811578723","https://openalex.org/W1517386993","https://openalex.org/W1533416326","https://openalex.org/W1545083717","https://openalex.org/W1553004968","https://openalex.org/W1586645951","https://openalex.org/W1606350000","https://openalex.org/W1607988020","https://openalex.org/W1920769845","https://openalex.org/W1972845249","https://openalex.org/W1990005915","https://openalex.org/W2015140204","https://openalex.org/W2019973879","https://openalex.org/W2054442733","https://openalex.org/W2070725064","https://openalex.org/W2094035326","https://openalex.org/W2104539041","https://openalex.org/W2114016253","https://openalex.org/W2126002878","https://openalex.org/W2130806807","https://openalex.org/W2131342762","https://openalex.org/W2136922672","https://openalex.org/W2137630452","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2156718662","https://openalex.org/W2158069733","https://openalex.org/W2160306971","https://openalex.org/W2163922914","https://openalex.org/W2163929346","https://openalex.org/W2170541567","https://openalex.org/W2292439652","https://openalex.org/W2293634267","https://openalex.org/W2296073425","https://openalex.org/W2394526247","https://openalex.org/W2398836258","https://openalex.org/W2400335852","https://openalex.org/W2408318243","https://openalex.org/W2479014774","https://openalex.org/W2913340405","https://openalex.org/W3202218022","https://openalex.org/W3204130541","https://openalex.org/W6605321065","https://openalex.org/W6607149552","https://openalex.org/W6636469245","https://openalex.org/W6679429981","https://openalex.org/W6683043316","https://openalex.org/W6696934422","https://openalex.org/W6712759826","https://openalex.org/W6802318714"],"related_works":["https://openalex.org/W4298130764","https://openalex.org/W2804364458","https://openalex.org/W2132641928","https://openalex.org/W4310225030","https://openalex.org/W2090259340","https://openalex.org/W1926736923","https://openalex.org/W2158836806","https://openalex.org/W2393816671","https://openalex.org/W3000197790","https://openalex.org/W2951720331"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,51,56,59,81,141],"use":[4,18],"of":[5,19,42,61,83,97,130],"multitask":[6,109],"learning":[7,110],"to":[8,76,119],"improve":[9],"context-dependent":[10],"deep":[11],"neural":[12],"network":[13],"(DNN)":[14],"acoustic":[15],"models.":[16],"The":[17,123],"hybrid":[20,121],"DNN":[21,43],"systems":[22],"with":[23],"clustered":[24],"triphone":[25],"targets":[26,44,57],"is":[27,125,150],"now":[28],"standard":[29,120],"in":[30,45,111],"automatic":[31],"speech":[32],"recognition.":[33],"However,":[34],"we":[35],"suggest":[36],"that":[37,67,105],"using":[38],"a":[39,62,94,100,128],"single":[40],"set":[41,96],"this":[46,78,112],"manner":[47,113],"may":[48,68],"not":[49,69],"be":[50,70],"most":[52],"effective":[53],"choice,":[54],"since":[55],"are":[58,136],"result":[60],"somewhat":[63],"arbitrary":[64],"clustering":[65],"process":[66],"optimal":[71],"for":[72],"discrimination.":[73],"We":[74,92],"propose":[75],"remedy":[77],"problem":[79],"through":[80,108],"addition":[82],"secondary":[84],"tasks":[85],"predicting":[86],"alternative":[87],"content-dependent":[88],"or":[89],"context-independent":[90],"targets.":[91],"present":[93],"comprehensive":[95],"experiments":[98],"on":[99],"lecture":[101],"recognition":[102],"task":[103],"showing":[104],"DNNs":[106],"trained":[107],"give":[114],"consistently":[115],"improved":[116],"performance":[117],"compared":[118],"DNNs.":[122],"technique":[124],"evaluated":[126],"across":[127],"range":[129],"data":[131],"and":[132,145],"output":[133],"sizes.":[134],"Improvements":[135],"seen":[137],"when":[138,147],"training":[139,149],"uses":[140],"cross":[142],"entropy":[143],"criterion":[144],"also":[146],"sequence":[148],"applied.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}