{"id":"https://openalex.org/W229594400","doi":"https://doi.org/10.21437/eurospeech.1995-103","title":"Speaker recognition using HMM composition in noisy environments","display_name":"Speaker recognition using HMM composition in noisy environments","publication_year":1995,"publication_date":"1995-09-18","ids":{"openalex":"https://openalex.org/W229594400","doi":"https://doi.org/10.21437/eurospeech.1995-103","mag":"229594400"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.1995-103","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1995-103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"4th European Conference on Speech Communication and Technology (Eurospeech 1995)","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/A5067714865","display_name":"Tomoko Matsui","orcid":"https://orcid.org/0000-0003-3201-6106"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoko Matsui","raw_affiliation_strings":["NTT Human Interface Laboratories, 3-9-11, Midori-cho, Musashino-shi, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Human Interface Laboratories, 3-9-11, Midori-cho, Musashino-shi, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015236406","display_name":"Tomohito Kanno","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohito Kanno","raw_affiliation_strings":["Tokyo Institute of Technology 2\u201012\u20101 Ookayama Meguro\u2010ku Tokyo Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology 2\u201012\u20101 Ookayama Meguro\u2010ku Tokyo Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009532108","display_name":"Sadaoki Furui","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sadaoki Furui","raw_affiliation_strings":["Tokyo Institute of Technology, 2-12-1, Ookayama, Meguro-ku, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, 2-12-1, Ookayama, Meguro-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5092,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.59310345,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"621","last_page":"624"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9919000267982483,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9919000267982483,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.989300012588501,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.9189261198043823},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8060950040817261},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7289684414863586},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6493430137634277},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6266767382621765},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5595192313194275},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.5445965528488159},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4995436668395996},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42180395126342773},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.414334774017334}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.9189261198043823},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8060950040817261},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7289684414863586},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6493430137634277},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6266767382621765},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5595192313194275},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.5445965528488159},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4995436668395996},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42180395126342773},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.414334774017334},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/eurospeech.1995-103","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1995-103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"4th European Conference on Speech Communication and Technology (Eurospeech 1995)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2144208207","https://openalex.org/W4389984014","https://openalex.org/W36105149","https://openalex.org/W1509309911","https://openalex.org/W2545131480","https://openalex.org/W2249138175","https://openalex.org/W1940231550","https://openalex.org/W2118860825","https://openalex.org/W4401661962","https://openalex.org/W2096510939"],"abstract_inverted_index":{"Abstract":[0],"This":[3],"paper":[4],"investigates":[5],"a":[6,26,51,55,59,64,109],"speaker":[7,30,52,61,89,110,125,139],"recognition":[8,140],"method":[9,38,85,122],"that":[10,96],"is":[11,22,41,71,106,112],"robust":[12],"against":[13],"background":[14],"noise.":[15,36],"In":[16],"noisy":[17,133],"environments,":[18],"one":[19],"important":[20],"issue":[21],"how":[23],"to":[24,33,73,123],"create":[25],"model":[27,46],"for":[28,35,102,141],"each":[29],"so":[31],"as":[32],"compensate":[34],"The":[37,94],"described":[39],"here":[40],"based":[42],"on":[43],"hidden":[44],"Markov":[45],"(HMM)":[47],"composition,":[48],"which":[49],"combines":[50],"HMM":[53,57,62,95],"and":[54,108,127],"noise-source":[56],"into":[58],"noise-added":[60,88],"with":[63,80,91],"particular":[65],"signal-to-noise":[66],"ratio":[67],"(SNR).":[68],"Since":[69],"it":[70],"difficult":[72],"measure":[74],"the":[75,98,103],"SNR":[76],"of":[77,120,132,144],"input":[78,104],"speech":[79,105,142],"non-stationary":[81],"noise":[82],"exactly,":[83],"this":[84,115,121],"creates":[86],"several":[87],"HMMs":[90],"various":[92,130],"SNRs.":[93],"has":[97],"highest":[99],"likelihood":[100,116],"value":[101],"selected,":[107],"decision":[111],"made":[113],"using":[114],"value.":[117],"Experimental":[118],"application":[119],"text-independent":[124],"identification":[126],"verification":[128],"in":[129,138],"kinds":[131],"environments":[134],"demonstrated":[135],"considerable":[136],"improvement":[137],"utterances":[143],"male":[145],"speakers.":[146]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}