{"id":"https://openalex.org/W2407320368","doi":"https://doi.org/10.21437/interspeech.2015-715","title":"Structured output layer with auxiliary targets for context-dependent acoustic modelling","display_name":"Structured output layer with auxiliary targets for context-dependent acoustic modelling","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2407320368","doi":"https://doi.org/10.21437/interspeech.2015-715","mag":"2407320368"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-715","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-715","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.pure.ed.ac.uk/ws/files/21398971/Swietojanski_Interspeech2015.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084169592","display_name":"Pawe\u0142 \u015awi\u0119toja\u0144ski","orcid":"https://orcid.org/0000-0001-5896-4505"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pawel Swietojanski","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102911387","display_name":"Peter Bell","orcid":"https://orcid.org/0000-0002-9597-9615"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peter Bell","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"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":["University of Edinburgh,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3605","last_page":"3609"},"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":0.9986000061035156,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9951000213623047,"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":0.8420500755310059},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.7351327538490295},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.615642249584198},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5983745455741882},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5982695817947388},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5671126842498779},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.552381694316864},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5517017841339111},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.540088951587677},{"id":"https://openalex.org/keywords/structuring","display_name":"Structuring","score":0.5210330486297607},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.475781112909317},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47396987676620483},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.45355066657066345},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40001624822616577},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13748574256896973}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8420500755310059},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.7351327538490295},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.615642249584198},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5983745455741882},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5982695817947388},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5671126842498779},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.552381694316864},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5517017841339111},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.540088951587677},{"id":"https://openalex.org/C2775945657","wikidata":"https://www.wikidata.org/wiki/Q381442","display_name":"Structuring","level":2,"score":0.5210330486297607},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.475781112909317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47396987676620483},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.45355066657066345},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40001624822616577},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13748574256896973},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2015-715","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-715","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/49823173-dd99-48d0-ac2d-bf6b2f93c030","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/portal/en/publications/structured-output-layer-with-auxiliary-targets-for-contextdependent-acoustic-modelling(49823173-dd99-48d0-ac2d-bf6b2f93c030).html","pdf_url":"https://www.pure.ed.ac.uk/ws/files/21398971/Swietojanski_Interspeech2015.pdf","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.712.3666","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.712.3666","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cstr.ed.ac.uk/downloads/publications/2015/Swietojanski_Interspeech2015.pdf","raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/49823173-dd99-48d0-ac2d-bf6b2f93c030","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/49823173-dd99-48d0-ac2d-bf6b2f93c030","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Swietojanski, P, Bell, P & Renals, S 2015, Structured Output Layer with Auxiliary Targets for Context-Dependent Acoustic Modelling. in INTERSPEECH 2015 16th Annual Conference of the International Speech Communication Association. International Speech Communication Association, pp. 3605-3609. < http://www.isca-speech.org/archive/interspeech_2015/i15_3605.html >","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/49823173-dd99-48d0-ac2d-bf6b2f93c030","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/portal/en/publications/structured-output-layer-with-auxiliary-targets-for-contextdependent-acoustic-modelling(49823173-dd99-48d0-ac2d-bf6b2f93c030).html","pdf_url":"https://www.pure.ed.ac.uk/ws/files/21398971/Swietojanski_Interspeech2015.pdf","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2407320368.pdf"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W17156489","https://openalex.org/W173856587","https://openalex.org/W1524333225","https://openalex.org/W1545083717","https://openalex.org/W1553004968","https://openalex.org/W1601269729","https://openalex.org/W1719257971","https://openalex.org/W1833744030","https://openalex.org/W1872489089","https://openalex.org/W1972845249","https://openalex.org/W1978660892","https://openalex.org/W1979447841","https://openalex.org/W1994606281","https://openalex.org/W2012897754","https://openalex.org/W2025198378","https://openalex.org/W2056445351","https://openalex.org/W2058641082","https://openalex.org/W2090861223","https://openalex.org/W2093794678","https://openalex.org/W2094035326","https://openalex.org/W2094147890","https://openalex.org/W2104539041","https://openalex.org/W2110798204","https://openalex.org/W2126002878","https://openalex.org/W2137630452","https://openalex.org/W2147768505","https://openalex.org/W2153395570","https://openalex.org/W2154642048","https://openalex.org/W2160306971","https://openalex.org/W2160650576","https://openalex.org/W2160815625","https://openalex.org/W2166637769","https://openalex.org/W2169189000","https://openalex.org/W2184135559","https://openalex.org/W2296073425","https://openalex.org/W2394932179","https://openalex.org/W2403731734","https://openalex.org/W2914746235"],"related_works":["https://openalex.org/W4394443292","https://openalex.org/W4251394462","https://openalex.org/W1580673008","https://openalex.org/W1510936208","https://openalex.org/W2486167009","https://openalex.org/W1595575899","https://openalex.org/W756498608","https://openalex.org/W2135201366","https://openalex.org/W4285395220","https://openalex.org/W2086773623"],"abstract_inverted_index":{"In":[0,24],"previous":[1],"work":[2],"we":[3,27],"have":[4,55,96],"introduced":[5],"a":[6,85],"multi-task":[7],"training":[8,102],"tech-nique":[9],"for":[10,133],"neural":[11,153],"network":[12],"acoustic":[13],"modelling,":[14],"in":[15],"which":[16],"context-dependent":[17,39,89,126],"and":[18,109,141],"context-independent":[19,45,50],"targets":[20],"are":[21,41,114,131],"jointly":[22],"learned.":[23],"this":[25,61],"paper,":[26],"extend":[28],"the":[29,33,38,44,49,58,72,79,111,139],"approach":[30,69],"by":[31],"structuring":[32],"out-put":[34],"layer":[35],"such":[36],"that":[37,76],"outputs":[40],"depen-dent":[42],"on":[43],"outputs,":[46],"thus":[47],"using":[48,138],"predictions":[51],"at":[52],"run-time.":[53],"We":[54,95],"also":[56],"investigated":[57],"applicability":[59],"of":[60,88,101],"idea":[62],"to":[63,70,78,106,118,122],"unsupervised":[64],"speaker":[65],"adapta-tion":[66],"as":[67],"an":[68],"overcome":[71],"data":[73,92],"sparsity":[74],"issues":[75],"comes":[77],"fore":[80],"when":[81,91],"estimating":[82],"systems":[83],"with":[84,98],"large":[86,125,134],"num-ber":[87],"states,":[90],"is":[93],"limited.":[94],"experimented":[97],"various":[99],"amounts":[100],"material":[103],"(from":[104],"10":[105],"300":[107],"hours)":[108],"find":[110],"proposed":[112],"techniques":[113],"particu-larly":[115],"well":[116],"suited":[117],"data-constrained":[119],"conditions":[120],"allowing":[121],"bet-ter":[123],"utilise":[124],"state-clustered":[127],"trees.":[128],"Exper-imental":[129],"results":[130],"reported":[132],"vocabulary":[135],"speech":[136],"recog-nition":[137],"Switchboard":[140],"TED":[142],"corpora.":[143],"Index":[144],"Terms:":[145],"multitask":[146],"learning,":[147],"structured":[148],"output":[149],"layer,":[150],"adap-tation,":[151],"deep":[152],"networks":[154]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":9}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}