{"id":"https://openalex.org/W208561639","doi":"https://doi.org/10.21437/interspeech.2004-569","title":"Speech recognition for multiple non-native accent groups with speaker-group-dependent acoustic models","display_name":"Speech recognition for multiple non-native accent groups with speaker-group-dependent acoustic models","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W208561639","doi":"https://doi.org/10.21437/interspeech.2004-569","mag":"208561639"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-569","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-569","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","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/A5058481406","display_name":"Tobias Cincarek","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tobias Cincarek","raw_affiliation_strings":["Advanced Telecommunications Research Institute International"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Telecommunications Research Institute International","institution_ids":["https://openalex.org/I4210104143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020458334","display_name":"Rainer Gruhn","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rainer Gruhn","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.441,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.54306022,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1509","last_page":"1512"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9984999895095825,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9940999746322632,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7509456872940063},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7395275235176086},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.676296591758728},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.629567563533783},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5405653119087219},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.497816801071167},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.4430640637874603},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.43067222833633423},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42415738105773926},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3959580063819885},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3764238953590393},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08611705899238586}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7509456872940063},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7395275235176086},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.676296591758728},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.629567563533783},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5405653119087219},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.497816801071167},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4430640637874603},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.43067222833633423},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42415738105773926},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3959580063819885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3764238953590393},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08611705899238586},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2004-569","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-569","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"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":9,"referenced_works":["https://openalex.org/W73469759","https://openalex.org/W191354409","https://openalex.org/W2095833672","https://openalex.org/W2100668800","https://openalex.org/W2110530876","https://openalex.org/W2150106068","https://openalex.org/W2169883442","https://openalex.org/W2295754094","https://openalex.org/W2799061466"],"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/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"the":[3,37,76,86,91,100],"recognition":[4],"performance":[5],"for":[6,22,55,127],"non-native":[7,30,147],"English":[8],"speech":[9,65],"with":[10,63,99,142],"two":[11],"different":[12],"kinds":[13],"of":[14,29,40,69,78,93,103],"speaker-groupdependent":[15],"acoustic":[16,47,53],"models":[17,48],"is":[18,43,59,106,120],"investigated.":[19],"The":[20,52],"approaches":[21],"creating":[23],"speaker":[24,50,57,105],"groups":[25],"include":[26],"knowledge-based":[27],"grouping":[28],"speakers":[31],"by":[32,61],"their":[33],"first":[34],"language,":[35],"and":[36,114,137,144],"automatic":[38],"clustering":[39],"speakers.":[41,139],"Clustering":[42],"based":[44],"on":[45],"speakerdependent":[46,143],"in":[49,122],"Eigenspace.":[51],"model":[54,95,148],"each":[56],"group":[58],"obtained":[60],"bootstrapping":[62],"pre-segmented":[64],"data":[66],"or":[67,88],"adaptation":[68,89],"a":[70,79,94,123],"speakerindependent":[71],"native":[72],"baseline":[73],"model.":[74],"For":[75],"decoding":[77,116],"nonnative":[80],"speaker\u2019s":[81],"utterance":[82],"not":[83],"seen":[84],"during":[85],"training":[87],"phase,":[90],"selection":[92,110],"suitable":[96],"to":[97],"cope":[98],"accent":[101,130],"characteristics":[102],"that":[104],"necessary.":[107],"Here,":[108],"ideal":[109],"via":[111],"an":[112,145],"oracle":[113],"parallel":[115],"are":[117],"examined.":[118],"Evaluation":[119],"conducted":[121],"hotel":[124],"reservation":[125],"task":[126],"five":[128],"major":[129],"groups,":[131],"including":[132],"German,":[133],"French,":[134],"Indonesian,":[135],"Chinese":[136],"Japanese":[138],"Recognition":[140],"results":[141],"accent-independent":[146],"will":[149],"also":[150],"be":[151],"reported.":[152]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}