{"id":"https://openalex.org/W2750527898","doi":"https://doi.org/10.21437/interspeech.2017-1365","title":"Factorised Representations for Neural Network Adaptation to Diverse Acoustic Environments","display_name":"Factorised Representations for Neural Network Adaptation to Diverse Acoustic Environments","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2750527898","doi":"https://doi.org/10.21437/interspeech.2017-1365","mag":"2750527898"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-1365","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1365","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/1ce22a37-319f-46a4-8c66-8303d4434e3b","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035806297","display_name":"Joachim Fainberg","orcid":"https://orcid.org/0000-0002-4669-7136"},"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":true,"raw_author_name":"Joachim Fainberg","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, United Kingdom"],"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","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":["The Centre for Speech Technology Research, University of Edinburgh, United Kingdom"],"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","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":["The Centre for Speech Technology Research, University of Edinburgh, United Kingdom"],"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5035806297"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":1.2384,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.84538469,"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":"749","last_page":"753"},"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":0.9980999827384949,"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":0.993399977684021,"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":0.8189221620559692},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7519165277481079},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6116685271263123},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.602320671081543},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5805436372756958},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5557695627212524},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42924410104751587},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4277636408805847},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4117279350757599}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8189221620559692},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7519165277481079},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6116685271263123},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.602320671081543},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5805436372756958},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5557695627212524},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42924410104751587},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4277636408805847},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4117279350757599},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2017-1365","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1365","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/1ce22a37-319f-46a4-8c66-8303d4434e3b","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/1ce22a37-319f-46a4-8c66-8303d4434e3b","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":"Fainberg, J, Renals, S & Bell, P 2017, Factorised representations for neural network adaptation to diverse acoustic environments. in Proceedings Interspeech 2017. Interspeech, International Speech Communication Association, pp. 749-753, Interspeech 2017, Stockholm, Sweden, 20/08/17. https://doi.org/10.21437/Interspeech.2017-1365","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/1ce22a37-319f-46a4-8c66-8303d4434e3b","is_oa":false,"landing_page_url":"https://www.research.ed.ac.uk/portal/en/publications/factorised-representations-for-neural-network-adaptation-to-diverse-acoustic-environments(1ce22a37-319f-46a4-8c66-8303d4434e3b).html","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/1ce22a37-319f-46a4-8c66-8303d4434e3b","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/1ce22a37-319f-46a4-8c66-8303d4434e3b","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":"Fainberg, J, Renals, S & Bell, P 2017, Factorised representations for neural network adaptation to diverse acoustic environments. in Proceedings Interspeech 2017. Interspeech, International Speech Communication Association, pp. 749-753, Interspeech 2017, Stockholm, Sweden, 20/08/17. https://doi.org/10.21437/Interspeech.2017-1365","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"display_name":"Climate action","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1492775261","https://openalex.org/W1513862252","https://openalex.org/W1524333225","https://openalex.org/W1665214252","https://openalex.org/W1983108229","https://openalex.org/W2002342963","https://openalex.org/W2006200410","https://openalex.org/W2026369565","https://openalex.org/W2048526313","https://openalex.org/W2079623482","https://openalex.org/W2117239706","https://openalex.org/W2135145707","https://openalex.org/W2187089797","https://openalex.org/W2239847623","https://openalex.org/W2294327763","https://openalex.org/W2403307129","https://openalex.org/W2404147237","https://openalex.org/W2404568753","https://openalex.org/W2468324704","https://openalex.org/W2508162385"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000","https://openalex.org/W2748922771","https://openalex.org/W1987128138","https://openalex.org/W2743976221"],"abstract_inverted_index":{"Adapting":[0],"acoustic":[1,53],"models":[2],"jointly":[3],"to":[4,12,37,55,66,86],"both":[5,134],"speaker":[6,22,44,68],"and":[7,45,130,140],"environment":[8,24,46,70,103],"has":[9],"been":[10],"shown":[11],"be":[13,29,34],"effective.":[14],"In":[15],"many":[16],"realistic":[17],"scenarios,":[18],"however,":[19],"either":[20,88],"the":[21,49,96,106,114,128,142,149],"or":[23,31,69,90],"at":[25],"test":[26,132],"time":[27],"might":[28],"unknown,":[30],"there":[32],"may":[33],"insufficient":[35],"data":[36],"learn":[38],"a":[39],"joint":[40],"transform.":[41],"Generating":[42],"independent":[43],"transforms":[47],"improves":[48],"match":[50],"of":[51,127],"an":[52],"model":[54],"unseen":[56],"combinations.":[57],"Using":[58,113],"i-vectors,":[59],"we":[60,79,117],"demonstrate":[61],"that":[62],"it":[63],"is":[64,138],"possible":[65],"factorise":[67],"information":[71],"using":[72],"multi-condition":[73],"training":[74],"with":[75,102],"neural":[76],"networks.":[77],"Specifically,":[78],"extract":[80],"bottleneck":[81],"features":[82],"from":[83,105],"networks":[84],"trained":[85],"classify":[87],"speakers":[89],"environments.":[91],"We":[92],"perform":[93],"experiments":[94],"on":[95,124],"Wall":[97],"Street":[98],"Journal":[99],"corpus":[100],"combined":[101],"noise":[104],"Diverse":[107],"Environments":[108],"Multichannel":[109],"Acoustic":[110],"Noise":[111],"Database.":[112],"factorised":[115],"i-vectors":[116],"show":[118],"improvements":[119],"in":[120,148],"word":[121],"error":[122],"rates":[123],"perturbed":[125],"versions":[126],"eval92":[129],"dev93":[131],"sets,":[133],"when":[135,141],"one":[136],"factor":[137],"missing":[139],"factors":[143],"are":[144],"seen":[145],"but":[146],"not":[147],"desired":[150],"combination.":[151]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}