{"id":"https://openalex.org/W2397381476","doi":"https://doi.org/10.1109/icassp.2016.7472629","title":"Combining i-vector representation and structured neural networks for rapid adaptation","display_name":"Combining i-vector representation and structured neural networks for rapid adaptation","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2397381476","doi":"https://doi.org/10.1109/icassp.2016.7472629","mag":"2397381476"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.repository.cam.ac.uk/bitstreams/802c7a2c-8bba-4858-a5b6-205e048d4e93/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101579713","display_name":"Chunyang Wu","orcid":"https://orcid.org/0000-0002-0269-3555"},"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":true,"raw_author_name":"Chunyang Wu","raw_affiliation_strings":["Engineering Dept, Cambridge University, Cambridge, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering Dept, Cambridge University, Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006537074","display_name":"Penny Karanasou","orcid":"https://orcid.org/0000-0003-1939-4161"},"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":"Penny Karanasou","raw_affiliation_strings":["Engineering Dept, Cambridge University, Cambridge, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering Dept, Cambridge University, Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050766679","display_name":"Mark Gales","orcid":"https://orcid.org/0000-0002-5311-8219"},"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":"Mark J. F. Gales","raw_affiliation_strings":["Engineering Dept, Cambridge University, Cambridge, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering Dept, Cambridge University, Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101579713"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":2.6507,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.91859696,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5000","last_page":"5004"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9995999932289124,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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":0.7705091238021851},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6256108283996582},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5579615235328674},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5285455584526062},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5232875943183899},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5027000904083252},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.4944298267364502},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.48417928814888},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4803130030632019},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.47737881541252136},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.46458226442337036},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.46342360973358154},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43692561984062195},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.43537044525146484},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4325401484966278},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43220239877700806},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35925087332725525},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.29859280586242676},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12799951434135437}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7705091238021851},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6256108283996582},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5579615235328674},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5285455584526062},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5232875943183899},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5027000904083252},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.4944298267364502},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.48417928814888},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4803130030632019},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.47737881541252136},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.46458226442337036},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46342360973358154},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43692561984062195},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.43537044525146484},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4325401484966278},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43220239877700806},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35925087332725525},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29859280586242676},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12799951434135437},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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:10.1109/icassp.2016.7472629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:www.repository.cam.ac.uk:1810/274295","is_oa":true,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/274295","pdf_url":"https://www.repository.cam.ac.uk/bitstreams/802c7a2c-8bba-4858-a5b6-205e048d4e93/download","source":{"id":"https://openalex.org/S4306401777","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Object"},{"id":"pmh:oai:generic.eprints.org:788326","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/788326/","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"},{"id":"doi:10.17863/cam.21420","is_oa":true,"landing_page_url":"https://doi.org/10.17863/cam.21420","pdf_url":null,"source":{"id":"https://openalex.org/S7407050737","display_name":"Apollo","issn_l":null,"issn":[],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:www.repository.cam.ac.uk:1810/274295","is_oa":true,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/274295","pdf_url":"https://www.repository.cam.ac.uk/bitstreams/802c7a2c-8bba-4858-a5b6-205e048d4e93/download","source":{"id":"https://openalex.org/S4306401777","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Object"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2531681599","display_name":null,"funder_award_id":"W911NF-12-C-0012","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"},{"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"},{"id":"https://openalex.org/G5259331294","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"}],"funders":[{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2397381476.pdf","grobid_xml":"https://content.openalex.org/works/W2397381476.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W82936479","https://openalex.org/W567546468","https://openalex.org/W1218987319","https://openalex.org/W1493888297","https://openalex.org/W1513820424","https://openalex.org/W1539668574","https://openalex.org/W1567690964","https://openalex.org/W1571447047","https://openalex.org/W1943324956","https://openalex.org/W1961429348","https://openalex.org/W1985371235","https://openalex.org/W1993409002","https://openalex.org/W2002342963","https://openalex.org/W2041823554","https://openalex.org/W2069631319","https://openalex.org/W2079623482","https://openalex.org/W2080005694","https://openalex.org/W2090320273","https://openalex.org/W2094147890","https://openalex.org/W2147768505","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2395655916","https://openalex.org/W2396422584","https://openalex.org/W2397860787","https://openalex.org/W2403307129","https://openalex.org/W6615969787","https://openalex.org/W6632343627","https://openalex.org/W6712213709","https://openalex.org/W6712565394"],"related_works":["https://openalex.org/W1999699871","https://openalex.org/W4225124612","https://openalex.org/W2043806667","https://openalex.org/W2021633306","https://openalex.org/W2006801911","https://openalex.org/W2033669961","https://openalex.org/W2971899271","https://openalex.org/W1972167985","https://openalex.org/W209733029","https://openalex.org/W3019226033"],"abstract_inverted_index":{"Rapid":[0],"adaptation":[1],"of":[2,20,54,69,76,96,109,150,193],"deep":[3],"neural":[4,36],"networks":[5,37],"(DNNs)":[6],"with":[7,72],"limited":[8],"unsupervised":[9],"data":[10,152,163],"remains":[11],"a":[12,139],"significant":[13],"challenge.":[14],"This":[15,113],"paper":[16],"investigates":[17],"the":[18,55,59,66,70,73,77,86,91,97,106,110,115,158,167,191],"combination":[19],"two":[21],"schemes":[22,44,184],"that":[23],"have":[24],"been":[25],"proposed":[26],"to":[27,58,64,84,93,104,166,187,190],"address":[28],"this":[29],"problem:":[30],"i-vector":[31,71],"representations":[32],"and":[33,89,122,134,197],"multi-basis":[34],"adaptive":[35],"(MBANNs).":[38],"Two":[39,147],"approaches":[40,129],"for":[41,117],"combining":[42],"these":[43,183],"together":[45],"are":[46,102,130,153],"described.":[47],"The":[48,61,80,155,170,179],"first":[49,156],"uses":[50],"i-vectors":[51,101],"as":[52],"one":[53],"input":[56],"features":[57],"MBANN.":[60],"purpose":[62],"is":[63,175,185],"combine":[65],"speaker":[67],"representation":[68],"network":[74],"interpolation":[75,107],"MBANN":[78,98,111],"scheme.":[79,99,112],"second":[81],"approach":[82],"aims":[83],"reduce":[85],"computational":[87],"cost,":[88],"improve":[90],"robustness":[92],"hypothesis":[94],"errors,":[95],"Here":[100],"used":[103],"predict":[105],"weights":[108],"removes":[114],"need":[116],"an":[118],"initial":[119],"decoding":[120],"pass,":[121],"alignment,":[123],"which":[124],"was":[125],"previously":[126],"used.":[127],"These":[128],"evaluated":[131],"using":[132],"acoustic":[133],"language":[135],"models":[136],"trained":[137],"on":[138],"U.S.":[140],"English":[141],"Broadcast":[142],"News":[143],"(BN)":[144],"transcription":[145],"task.":[146],"distinct":[148],"sets":[149],"test":[151,162],"examined.":[154],"from":[157,176,182],"BN":[159],"task,":[160],"yields":[161],"acoustically":[164,172],"matched":[165],"training":[168,196],"data.":[169],"second,":[171],"mismatched,":[173],"set":[174],"Youtube":[177],"videos.":[178],"performance":[180],"gains":[181],"found":[186],"be":[188],"sensitive":[189],"level":[192],"mismatch":[194],"between":[195],"test.":[198]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":5}],"updated_date":"2026-05-11T08:15:01.531666","created_date":"2025-10-10T00:00:00"}