{"id":"https://openalex.org/W2889500720","doi":"https://doi.org/10.21437/interspeech.2018-1707","title":"Visualizing Phoneme Category Adaptation in Deep Neural Networks","display_name":"Visualizing Phoneme Category Adaptation in Deep Neural Networks","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2889500720","doi":"https://doi.org/10.21437/interspeech.2018-1707","mag":"2889500720"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1707","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1707","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","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/A5048860892","display_name":"Odette Scharenborg","orcid":"https://orcid.org/0000-0003-0693-8852"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Odette Scharenborg","raw_affiliation_strings":["Delft University of Technology"],"affiliations":[{"raw_affiliation_string":"Delft University of Technology","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058200006","display_name":"Sebastian Tiesmeyer","orcid":"https://orcid.org/0000-0002-0492-1523"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sebastian Tiesmeyer","raw_affiliation_strings":["Centre for Language Studies"],"affiliations":[{"raw_affiliation_string":"Centre for Language Studies","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["Electrical and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050632169","display_name":"Najim Dehak","orcid":"https://orcid.org/0000-0002-4489-5753"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Najim Dehak","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5048860892"],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":1.303,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.85365523,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1482","last_page":"1486"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"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":0.6931458711624146},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6653482913970947},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6403527855873108},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5783644318580627},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5690745115280151},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.49840569496154785},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4602107107639313},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.0856005847454071}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6931458711624146},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6653482913970947},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6403527855873108},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5783644318580627},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5690745115280151},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.49840569496154785},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4602107107639313},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0856005847454071},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2018-1707","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1707","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:tudelft.nl:uuid:33a28b86-c5dc-4d14-bfae-08d3dcf2cdbf","is_oa":false,"landing_page_url":"http://resolver.tudelft.nl/uuid:33a28b86-c5dc-4d14-bfae-08d3dcf2cdbf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"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 paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W45652944","https://openalex.org/W156258841","https://openalex.org/W1520968739","https://openalex.org/W1597739853","https://openalex.org/W1978541527","https://openalex.org/W2002342963","https://openalex.org/W2010362084","https://openalex.org/W2010418158","https://openalex.org/W2027466120","https://openalex.org/W2052922189","https://openalex.org/W2095458199","https://openalex.org/W2096162685","https://openalex.org/W2121696946","https://openalex.org/W2124882279","https://openalex.org/W2125482195","https://openalex.org/W2133590932","https://openalex.org/W2160003195","https://openalex.org/W2338667069","https://openalex.org/W2509372369"],"related_works":["https://openalex.org/W189527659","https://openalex.org/W1554605283","https://openalex.org/W1597064740","https://openalex.org/W2116397056","https://openalex.org/W2076610045","https://openalex.org/W1927670981","https://openalex.org/W1522515376","https://openalex.org/W2261144205","https://openalex.org/W2160818304","https://openalex.org/W1605182496"],"abstract_inverted_index":{"Both":[0],"human":[1,68,156],"listeners":[2],"and":[3,176,183,196],"machines":[4],"need":[5],"to":[6,43,56,62,109],"adapt":[7,42],"their":[8],"sound":[9],"categories":[10],"whenever":[11],"a":[12,34,45,59,65,119,161,166],"new":[13],"speaker":[14],"is":[15,20,30,170],"encountered.":[16],"This":[17],"perceptual":[18,69,102,157,167],"learning":[19,158],"driven":[21],"by":[22,75,131,141,148],"lexical":[23],"information.":[24],"The":[25,104,123],"aim":[26],"of":[27,48,67,80,98,135,165],"this":[28],"paper":[29],"two-fold:":[31],"investigate":[32,58],"whether":[33],"deep":[35],"neural":[36],"network-based":[37],"(DNN)":[38],"ASR":[39,198],"system":[40],"can":[41,185],"only":[44,130],"few":[46,120],"examples":[47],"ambiguous":[49],"speech":[50,195],"as":[51,64],"humans":[52,184,193],"have":[53],"been":[54],"found":[55],"do;":[57],"DNN\u2019s":[60],"ability":[61],"serve":[63],"model":[66],"learning.":[70,103],"Crucially,":[71],"we":[72],"do":[73],"so":[74],"looking":[76],"at":[77,86],"intermediate":[78,171],"levels":[79],"phoneme":[81],"category":[82,116,127],"adaptation":[83],"rather":[84],"than":[85],"the":[87,92,95,99,133,136,143,149,153,173,177,191],"output":[88,137],"level.":[89],"We":[90],"visualize":[91],"activations":[93],"in":[94],"hidden":[96,150],"layers":[97],"DNN":[100,111,124],"during":[101],"results":[105],"show":[106],"that,":[107],"similar":[108,162],"humans,":[110],"systems":[112],"learn":[113],"speaker-adapted":[114],"phone":[115],"boundaries":[117,128],"from":[118],"labeled":[121],"examples.":[122],"adapts":[125],"its":[126],"not":[129],"adapting":[132,142],"weights":[134],"layer,":[138],"but":[139],"also":[140],"implicit":[144],"feature":[145],"maps":[146],"computed":[147],"layers,":[151],"suggesting":[152],"possibility":[154],"that":[155,169],"might":[159],"involve":[160],"nonlinear":[163],"distortion":[164],"space":[168],"between":[172,181],"acoustic":[174],"input":[175],"phonological":[178],"categories.":[179],"Comparisons":[180],"DNNs":[182],"thus":[186],"provide":[187],"valuable":[188],"insights":[189],"into":[190],"way":[192],"process":[194],"improve":[197],"technology.":[199]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}