{"id":"https://openalex.org/W1897092482","doi":"https://doi.org/10.1109/nnsp.2002.1030076","title":"Speaker normalization using HMM2","display_name":"Speaker normalization using HMM2","publication_year":2003,"publication_date":"2003-06-25","ids":{"openalex":"https://openalex.org/W1897092482","doi":"https://doi.org/10.1109/nnsp.2002.1030076","mag":"1897092482"},"language":"en","primary_location":{"id":"doi:10.1109/nnsp.2002.1030076","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nnsp.2002.1030076","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th IEEE Workshop on Neural Networks for Signal Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/82771","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053319645","display_name":"Shajith Ikbal","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"S. Ikbal","raw_affiliation_strings":["Dalle Molle Institute for Perceptual Artificial Intelligence (IDIAP), Swiss Federal Institute of Technology, Lausanne (EPFL), Switzerland"],"affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Perceptual Artificial Intelligence (IDIAP), Swiss Federal Institute of Technology, Lausanne (EPFL), Switzerland","institution_ids":["https://openalex.org/I2614128279","https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000851749","display_name":"Katrin Weber","orcid":"https://orcid.org/0000-0002-5821-1287"},"institutions":[{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]},{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"K. Weber","raw_affiliation_strings":["Dalle Molle Institute for Perceptual Artificial Intelligence (IDIAP), Swiss Federal Institute of Technology, Lausanne (EPFL), Switzerland","Dalle Molle Institute for Perceptual Artificial Intelligence, Switzerland"],"affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Perceptual Artificial Intelligence (IDIAP), Swiss Federal Institute of Technology, Lausanne (EPFL), Switzerland","institution_ids":["https://openalex.org/I2614128279","https://openalex.org/I5124864"]},{"raw_affiliation_string":"Dalle Molle Institute for Perceptual Artificial Intelligence, Switzerland","institution_ids":["https://openalex.org/I2614128279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108291827","display_name":"H. Bourlard","orcid":null},"institutions":[{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]},{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"H. Bourlard","raw_affiliation_strings":["Dalle Molle Institute for Perceptual Artificial Intelligence (IDIAP), Swiss Federal Institute of Technology, Lausanne (EPFL), Switzerland","Dalle Molle Institute for Perceptual Artificial Intelligence, Switzerland"],"affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Perceptual Artificial Intelligence (IDIAP), Swiss Federal Institute of Technology, Lausanne (EPFL), Switzerland","institution_ids":["https://openalex.org/I2614128279","https://openalex.org/I5124864"]},{"raw_affiliation_string":"Dalle Molle Institute for Perceptual Artificial Intelligence, Switzerland","institution_ids":["https://openalex.org/I2614128279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053319645"],"corresponding_institution_ids":["https://openalex.org/I2614128279","https://openalex.org/I5124864"],"apc_list":null,"apc_paid":null,"fwci":1.4039,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.84381981,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":null,"first_page":"647","last_page":"656"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9970999956130981,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9919000267982483,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9359445571899414},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.8239116668701172},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6783722639083862},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.665733814239502},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6095983982086182},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5781365633010864},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5443782806396484},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5227680206298828},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5005934238433838},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4964144825935364},{"id":"https://openalex.org/keywords/piecewise","display_name":"Piecewise","score":0.48248863220214844},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.47733670473098755},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20161586999893188}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.9359445571899414},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8239116668701172},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6783722639083862},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.665733814239502},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6095983982086182},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5781365633010864},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5443782806396484},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5227680206298828},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5005934238433838},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4964144825935364},{"id":"https://openalex.org/C164660894","wikidata":"https://www.wikidata.org/wiki/Q2037833","display_name":"Piecewise","level":2,"score":0.48248863220214844},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.47733670473098755},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20161586999893188},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/nnsp.2002.1030076","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nnsp.2002.1030076","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th IEEE Workshop on Neural Networks for Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.7.4318","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.7.4318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ftp://ftp.idiap.ch/pub/reports/2002/rr02-15.ps.gz","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:82771","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/82771","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:infoscience.epfl.ch:82831","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/82831","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:82771","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/82771","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"score":0.6399999856948853,"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":14,"referenced_works":["https://openalex.org/W1500059311","https://openalex.org/W1543221393","https://openalex.org/W1553004968","https://openalex.org/W1568915220","https://openalex.org/W1577024852","https://openalex.org/W1608451537","https://openalex.org/W2104663520","https://openalex.org/W2106119541","https://openalex.org/W2121981798","https://openalex.org/W2145806376","https://openalex.org/W4300771300","https://openalex.org/W6632555812","https://openalex.org/W6634612644","https://openalex.org/W6844555276"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W4247736853","https://openalex.org/W1992908141","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863"],"abstract_inverted_index":{"We":[0],"present":[1,136],"an":[2,11],"HMM2":[3,18],"based":[4,110],"method":[5],"for":[6,124],"speaker":[7,73,91,127,142],"normalization.":[8],"Introduced":[9],"as":[10],"extension":[12],"of":[13,27,38,59,98,101,120,133,151],"hidden":[14],"Markov":[15],"model":[16],"(HMM),":[17],"differentiates":[19],"itself":[20],"from":[21],"the":[22,28,43,54,63,80,90,102,116,126,137,149,152],"regular":[23,121],"HMM":[24,50,109,122],"in":[25,42,115],"terms":[26],"emission":[29,48],"density":[30],"modeling,":[31],"which":[32],"is":[33,86,113],"done":[34],"by":[35],"a":[36],"set":[37],"state-dependent":[39],"HMMs":[40],"working":[41],"feature":[44,64,117],"vector":[45],"space.":[46],"The":[47],"modeling":[49],"aims":[51],"at":[52],"maximizing":[53],"likelihood":[55],"through":[56,94,146],"optimal":[57],"alignment":[58,81],"its":[60],"states":[61],"across":[62],"components.":[65],"This":[66],"property":[67],"makes":[68],"it":[69,85],"potentially":[70],"useful":[71],"to":[72,77,88],"normalization,":[74],"when":[75],"applied":[76],"spectrum.":[78,103],"With":[79],"information":[82],"we":[83,135],"get,":[84],"possible":[87],"normalize":[89],"related":[92,128],"variations":[93],"piecewise":[95],"linear":[96],"warping":[97,112],"frequency":[99],"axis":[100],"In":[104],"our":[105],"case,":[106],"(emission":[107],"modeling)":[108],"spectral":[111],"employed":[114],"extraction":[118],"block":[119],"framework":[123],"normalizing":[125],"variabilities.":[129],"After":[130],"brief":[131],"description":[132],"HMM2,":[134],"general":[138],"approach":[139],"towards":[140],"HMM2-based":[141],"normalization":[143],"and":[144],"show,":[145],"preliminary":[147],"experiments,":[148],"pertinence":[150],"approach.":[153]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}