{"id":"https://openalex.org/W2407299475","doi":"https://doi.org/10.1109/icassp.2016.7472689","title":"DNN speaker adaptation using parameterised sigmoid and ReLU hidden activation functions","display_name":"DNN speaker adaptation using parameterised sigmoid and ReLU hidden activation functions","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2407299475","doi":"https://doi.org/10.1109/icassp.2016.7472689","mag":"2407299475"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472689","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472689","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"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007989522","display_name":"C. Zhang","orcid":"https://orcid.org/0000-0002-2173-6872"},"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":"C. Zhang","raw_affiliation_strings":["Cambridge University Engineering Dept., Cambridge, U.K"],"affiliations":[{"raw_affiliation_string":"Cambridge University Engineering Dept., Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002191410","display_name":"Philip C. Woodland","orcid":"https://orcid.org/0000-0001-9069-0225"},"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":"P. C. Woodland","raw_affiliation_strings":["Cambridge University Engineering Dept., Cambridge, U.K"],"affiliations":[{"raw_affiliation_string":"Cambridge University Engineering Dept., Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5007989522"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":12.8542,"has_fulltext":false,"cited_by_count":63,"citation_normalized_percentile":{"value":0.98637987,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T10860","display_name":"Speech and Audio Processing","score":0.9940000176429749,"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/T11309","display_name":"Music and Audio Processing","score":0.9897000193595886,"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/sigmoid-function","display_name":"Sigmoid function","score":0.9322289824485779},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7346011996269226},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6816256046295166},{"id":"https://openalex.org/keywords/activation-function","display_name":"Activation function","score":0.5991755127906799},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5605247020721436},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5538948178291321},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5433521866798401},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5194751620292664},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4884423315525055},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4007960855960846},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3623405694961548},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.11188453435897827}],"concepts":[{"id":"https://openalex.org/C81388566","wikidata":"https://www.wikidata.org/wiki/Q526668","display_name":"Sigmoid function","level":3,"score":0.9322289824485779},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7346011996269226},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6816256046295166},{"id":"https://openalex.org/C38365724","wikidata":"https://www.wikidata.org/wiki/Q4677469","display_name":"Activation function","level":3,"score":0.5991755127906799},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5605247020721436},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5538948178291321},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5433521866798401},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5194751620292664},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4884423315525055},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4007960855960846},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3623405694961548},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.11188453435897827},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472689","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472689","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W26405188","https://openalex.org/W82936479","https://openalex.org/W567546468","https://openalex.org/W1513820424","https://openalex.org/W1513862252","https://openalex.org/W1529602138","https://openalex.org/W1567690964","https://openalex.org/W1770758908","https://openalex.org/W1985371235","https://openalex.org/W1989549063","https://openalex.org/W1992912377","https://openalex.org/W1993409002","https://openalex.org/W2002342963","https://openalex.org/W2010362084","https://openalex.org/W2012897754","https://openalex.org/W2036351241","https://openalex.org/W2056825827","https://openalex.org/W2079623482","https://openalex.org/W2080005694","https://openalex.org/W2094147890","https://openalex.org/W2160306971","https://openalex.org/W2172097686","https://openalex.org/W2184045248","https://openalex.org/W2288402171","https://openalex.org/W2395596777","https://openalex.org/W2397450537","https://openalex.org/W2401396087","https://openalex.org/W2403307129","https://openalex.org/W2407320368","https://openalex.org/W2407698769","https://openalex.org/W2964182776","https://openalex.org/W6601083597","https://openalex.org/W6603403951","https://openalex.org/W6615969787","https://openalex.org/W6639822467","https://openalex.org/W6686210252","https://openalex.org/W6711726519","https://openalex.org/W6713250295","https://openalex.org/W6713403589","https://openalex.org/W6713606482","https://openalex.org/W6713701104"],"related_works":["https://openalex.org/W2032258609","https://openalex.org/W3024979424","https://openalex.org/W4283785902","https://openalex.org/W3032499992","https://openalex.org/W2041004593","https://openalex.org/W3134817226","https://openalex.org/W2895192346","https://openalex.org/W3110577345","https://openalex.org/W3136579697","https://openalex.org/W2811324119"],"abstract_inverted_index":{"This":[0,81],"paper":[1],"investigates":[2],"the":[3,56,72,108,120],"use":[4],"of":[5,74],"parameterised":[6,140],"sigmoid":[7,24,47,141],"and":[8,25,60,92,119,123,142],"rectified":[9],"linear":[10,42],"unit":[11,51,57],"(ReLU)":[12],"hidden":[13,50,76,148],"activation":[14,144],"functions":[15],"in":[16,112,132],"deep":[17],"neural":[18],"network":[19],"(DNN)":[20],"speaker":[21,34,63],"adaptation.":[22,150],"The":[23],"ReLU":[26,49,143],"parameterisation":[27],"schemes":[28],"from":[29],"a":[30,62],"previous":[31],"study":[32],"for":[33,78,146],"independent":[35],"(SI)":[36],"training":[37],"are":[38,136],"used.":[39],"An":[40],"adaptive":[41],"factor":[43],"associated":[44],"with":[45,126],"each":[46],"or":[48],"is":[52,84,110],"used":[53],"to":[54,86],"scale":[55],"output":[58],"value":[59],"create":[61],"dependent":[64],"(SD)":[65],"model.":[66],"Hence,":[67],"DNN":[68,89,116,128],"adaptation":[69,82,129],"becomes":[70],"re-weighting":[71],"importance":[73],"different":[75],"units":[77],"every":[79],"speaker.":[80],"scheme":[83],"applied":[85],"both":[87,113],"hybrid":[88],"acoustic":[90,117],"modelling":[91],"DNN-based":[93],"bottleneck":[94],"(BN)":[95],"feature":[96],"extraction.":[97],"Experiments":[98],"using":[99,139],"multi-genre":[100],"British":[101],"English":[102],"television":[103],"broadcast":[104],"data":[105],"show":[106],"that":[107],"technique":[109],"effective":[111],"directly":[114],"adapting":[115],"models":[118],"BN":[121],"features,":[122],"combines":[124],"well":[125],"other":[127],"techniques.":[130],"Reductions":[131],"word":[133],"error":[134],"rate":[135],"consistently":[137],"obtained":[138],"function":[145],"multiple":[147],"layer":[149]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}