{"id":"https://openalex.org/W2403731734","doi":"https://doi.org/10.21437/interspeech.2013-336","title":"Rapid and effective speaker adaptation of convolutional neural network based models for speech recognition","display_name":"Rapid and effective speaker adaptation of convolutional neural network based models for speech recognition","publication_year":2013,"publication_date":"2013-08-25","ids":{"openalex":"https://openalex.org/W2403731734","doi":"https://doi.org/10.21437/interspeech.2013-336","mag":"2403731734"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2013-336","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-336","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"},"type":"conference-paper","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/A5077733105","display_name":"Ossama Abdel\u2010Hamid","orcid":null},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ossama Abdel-Hamid","raw_affiliation_strings":["York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"York University","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101454723","display_name":"Hui Jiang","orcid":"https://orcid.org/0000-0003-4062-7206"},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hui Jiang","raw_affiliation_strings":["York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"York University","institution_ids":["https://openalex.org/I192455969"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I192455969"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":55,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1248","last_page":"1252"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9969000220298767,"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":0.9962999820709229,"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":0.8542647957801819},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7422881722450256},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.7395451068878174},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.7379317879676819},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6557305455207825},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5635156631469727},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4678196609020233},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4508804380893707},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4463229179382324},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.432778924703598},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42562994360923767}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8542647957801819},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7422881722450256},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.7395451068878174},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7379317879676819},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6557305455207825},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5635156631469727},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4678196609020233},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4508804380893707},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4463229179382324},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.432778924703598},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42562994360923767},{"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":2,"locations":[{"id":"doi:10.21437/interspeech.2013-336","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-336","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.701.8422","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.701.8422","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.yorku.ca/%7Eossama/pub/CNN_adapt.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W26405188","https://openalex.org/W1513862252","https://openalex.org/W1993409002","https://openalex.org/W1993882792","https://openalex.org/W2002342963","https://openalex.org/W2036242736","https://openalex.org/W2052248915","https://openalex.org/W2063689849","https://openalex.org/W2077804127","https://openalex.org/W2080005694","https://openalex.org/W2100969003","https://openalex.org/W2121981798","https://openalex.org/W2146871184","https://openalex.org/W2155273149","https://openalex.org/W2157711090","https://openalex.org/W2394932179","https://openalex.org/W2397860787"],"related_works":["https://openalex.org/W2155033763","https://openalex.org/W3134920593","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W2206035908","https://openalex.org/W2501000458","https://openalex.org/W1578749070","https://openalex.org/W2162158162","https://openalex.org/W2146842779","https://openalex.org/W2148099973"],"abstract_inverted_index":{"Recently,":[0],"we":[1,116,141,189],"have":[2],"proposed":[3,99],"a":[4,35,39,45,88,143],"novel":[5],"fast":[6,119],"adaptation":[7,24,68,93,120,131,145],"method":[8,19,78,100,132],"for":[9,34,53,164],"the":[10,67,98,106,118,127,137,162,170],"hybrid":[11],"DNN-HMM":[12],"models":[13,187],"in":[14,82,105,180],"speech":[15,32],"recognition":[16],"[1].":[17],"This":[18],"relies":[20],"on":[21,169],"learning":[22],"an":[23],"NN":[25,69],"that":[26,76,174],"is":[27,63,79,95],"capa-ble":[28],"of":[29,92,108,121,182],"transforming":[30],"input":[31],"features":[33],"certain":[36],"speaker":[37,41,47,55,128,148],"into":[38],"more":[40],"independent":[42],"space":[43],"given":[44],"suitable":[46],"code.":[48],"Speaker":[49],"codes":[50],"are":[51,177],"learned":[52],"each":[54],"during":[56],"adap-tation.":[57],"The":[58],"whole":[59],"multi-speaker":[60],"training":[61],"dataset":[62,172],"used":[64],"to":[65,133,136,160],"learn":[66],"weights.":[70,153],"Our":[71],"previous":[72],"work":[73,103],"has":[74],"shown":[75],"this":[77,114],"quite":[80,178],"effective":[81,179],"adapting":[83],"DNNs":[84],"even":[85,192],"when":[86],"only":[87],"very":[89],"small":[90],"amount":[91],"data":[94],"available.":[96],"However,":[97],"does":[101],"not":[102],"well":[104],"case":[107],"convo-lutional":[109],"neural":[110],"network":[111],"(CNN).":[112],"In":[113],"paper,":[115],"investigate":[117,142],"CNN":[122,138,184],"models.":[123],"We":[124],"first":[125],"modify":[126],"code":[129],"based":[130,185],"better":[134,193],"suit":[135],"struc-ture.":[139],"Moreover,":[140],"new":[144,165],"scheme":[146],"using":[147],"specific":[149],"adaptive":[150],"nodes":[151,158],"output":[152],"These":[154],"weights":[155],"scale":[156],"different":[157],"outputs":[159],"optimize":[161],"model":[163],"speakers.":[166],"Experimental":[167],"results":[168],"TIMIT":[171],"demon-strates":[173],"both":[175],"methods":[176,199],"terms":[181],"adapt-ing":[183],"acoustic":[186],"and":[188],"can":[190],"achieve":[191],"performance":[194],"by":[195],"combining":[196],"these":[197],"two":[198],"together.":[200]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":15},{"year":2014,"cited_by_count":13}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}