{"id":"https://openalex.org/W1961429348","doi":"https://doi.org/10.1109/icassp.2015.7178783","title":"Differentiable pooling for unsupervised speaker adaptation","display_name":"Differentiable pooling for unsupervised speaker adaptation","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1961429348","doi":"https://doi.org/10.1109/icassp.2015.7178783","mag":"1961429348"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178783","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178783","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/cd1d2b05-7c32-46ec-81ec-62b1fd0db42b","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":[{"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","Centre for Speech Technology Research, University of Edinburgh, EH8 9AB, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, EH8 9AB, UK","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","Centre for Speech Technology Research, University of Edinburgh, EH8 9AB, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, EH8 9AB, UK","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":null,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4305","last_page":"4309"},"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":0.9980000257492065,"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":0.9976999759674072,"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/pooling","display_name":"Pooling","score":0.852113664150238},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7537809610366821},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6770458221435547},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5918718576431274},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5809235572814941},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5783142447471619},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5625815987586975},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5501410365104675},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5500067472457886},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5496009588241577},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4983217716217041},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.4490547478199005},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4212478995323181},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4171258807182312},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.41497802734375},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4116251468658447},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09633111953735352}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.852113664150238},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7537809610366821},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6770458221435547},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5918718576431274},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5809235572814941},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5783142447471619},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5625815987586975},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5501410365104675},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5500067472457886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5496009588241577},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4983217716217041},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.4490547478199005},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4212478995323181},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4171258807182312},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.41497802734375},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4116251468658447},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09633111953735352},{"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp.2015.7178783","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178783","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.712.3945","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.712.3945","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_ICASSP2015.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.725.5178","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.725.5178","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://homepages.inf.ed.ac.uk/srenals/ps_icassp2015_gauss.pdf","raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/cd1d2b05-7c32-46ec-81ec-62b1fd0db42b","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/cd1d2b05-7c32-46ec-81ec-62b1fd0db42b","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 & Renals, S 2015, Differentiable pooling for unsupervised speaker adaptation. in Proceedings IEEE International Conference on Acoustics, Speech and Signal Processing.","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/cd1d2b05-7c32-46ec-81ec-62b1fd0db42b","is_oa":false,"landing_page_url":"https://www.research.ed.ac.uk/portal/en/publications/differentiable-pooling-for-unsupervised-speaker-adaptation(cd1d2b05-7c32-46ec-81ec-62b1fd0db42b).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/cd1d2b05-7c32-46ec-81ec-62b1fd0db42b","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/cd1d2b05-7c32-46ec-81ec-62b1fd0db42b","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 & Renals, S 2015, Differentiable pooling for unsupervised speaker adaptation. in Proceedings IEEE International Conference on Acoustics, Speech and Signal Processing.","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W811578723","https://openalex.org/W1513862252","https://openalex.org/W1524333225","https://openalex.org/W1537275613","https://openalex.org/W1553004968","https://openalex.org/W1864026867","https://openalex.org/W1872489089","https://openalex.org/W1968419113","https://openalex.org/W1968706335","https://openalex.org/W1981617403","https://openalex.org/W1989549063","https://openalex.org/W1993409002","https://openalex.org/W2002342963","https://openalex.org/W2010362084","https://openalex.org/W2026369565","https://openalex.org/W2036351241","https://openalex.org/W2056738732","https://openalex.org/W2061305730","https://openalex.org/W2079623482","https://openalex.org/W2087006792","https://openalex.org/W2089917322","https://openalex.org/W2091987367","https://openalex.org/W2094147890","https://openalex.org/W2112796928","https://openalex.org/W2116456623","https://openalex.org/W2139427956","https://openalex.org/W2147800946","https://openalex.org/W2149194912","https://openalex.org/W2150769028","https://openalex.org/W2156692643","https://openalex.org/W2160306971","https://openalex.org/W2160650576","https://openalex.org/W2160815625","https://openalex.org/W2162931300","https://openalex.org/W2169189000","https://openalex.org/W2172130635","https://openalex.org/W2198082746","https://openalex.org/W2251645580","https://openalex.org/W2294059674","https://openalex.org/W2403731734","https://openalex.org/W2404068704","https://openalex.org/W2917668649","https://openalex.org/W2962719052","https://openalex.org/W4293460823","https://openalex.org/W6631362777","https://openalex.org/W6639260565","https://openalex.org/W6639297342","https://openalex.org/W6670225552","https://openalex.org/W6677681515","https://openalex.org/W6683161958","https://openalex.org/W6683965311","https://openalex.org/W6687511127","https://openalex.org/W6696761078","https://openalex.org/W6713454745","https://openalex.org/W6759815381"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2099333848"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,18,43],"differentiable":[4],"pooling":[5],"mechanism":[6],"to":[7,30,80,87,107,123,131],"perform":[8],"model-based":[9],"neural":[10],"network":[11],"speaker":[12,134],"adaptation.":[13],"The":[14],"proposed":[15,90],"technique":[16],"learns":[17],"speaker-dependent":[19],"combination":[20],"of":[21,25,45,115],"activations":[22],"within":[23],"pools":[24],"hidden":[26,92],"units,":[27],"was":[28,84],"shown":[29],"work":[31,108],"well":[32,109],"unsupervised,":[33],"and":[34,83],"does":[35],"not":[36],"require":[37],"speaker-adaptive":[38],"training.":[39],"We":[40],"have":[41],"conducted":[42],"set":[44],"experiments":[46],"on":[47,70],"the":[48,55,62,88,125,132],"TED":[49],"talks":[50],"data,":[51],"as":[52],"used":[53],"in":[54],"IWSLT":[56,72],"evaluations.":[57],"Our":[58],"results":[59],"indicate":[60],"that":[61],"approach":[63],"can":[64],"reduce":[65],"word":[66],"error":[67],"rates":[68],"(WERs)":[69],"standard":[71],"test":[73],"sets":[74],"by":[75,99,127],"about":[76],"5-11%":[77],"relative":[78,129],"compared":[79,130],"speaker-independent":[81],"systems":[82],"found":[85,106],"complementary":[86],"recently":[89],"learning":[91],"units":[93],"contribution":[94],"(LHUC)":[95],"approach,":[96],"reducing":[97],"WER":[98,126],"6-13%":[100],"relative.":[101],"Both":[102],"methods":[103],"were":[104],"also":[105],"when":[110],"adapting":[111],"with":[112],"small":[113],"amounts":[114],"unsupervised":[116],"data":[117],"-":[118],"10":[119],"seconds":[120],"is":[121],"able":[122],"decrease":[124],"5%":[128],"baseline":[133],"independent":[135],"system.":[136]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}