{"id":"https://openalex.org/W2107228843","doi":"https://doi.org/10.1109/icme.2003.1220857","title":"Selection, parameter estimation, and discriminative training of hidden Markov models for general audio modeling","display_name":"Selection, parameter estimation, and discriminative training of hidden Markov models for general audio modeling","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W2107228843","doi":"https://doi.org/10.1109/icme.2003.1220857","mag":"2107228843"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2003.1220857","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2003.1220857","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.7916/d8h13bdp","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007970907","display_name":"Manuel Reyes Gomez","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"M.J. Reyes-Gomez","raw_affiliation_strings":["Department of Electrical Engineering, Columbia University, New York, NY, USA","Dept. of Electr. Eng, Columbia Univ., New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Dept. of Electr. Eng, Columbia Univ., New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055458377","display_name":"Daniel P. W. Ellis","orcid":"https://orcid.org/0000-0002-5076-4311"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D.P.W. Ellis","raw_affiliation_strings":["Department of Electrical Engineering, Columbia University, New York, NY, USA","Dept. of Electr. Eng, Columbia Univ., New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Dept. of Electr. Eng, Columbia Univ., New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5007970907"],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":2.9639,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.92122126,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"I","last_page":"73"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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/T11309","display_name":"Music and Audio Processing","score":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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":0.9961000084877014,"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/discriminative-model","display_name":"Discriminative model","score":0.880449652671814},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7969750165939331},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7485278844833374},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5970318913459778},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.5822001695632935},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5773757696151733},{"id":"https://openalex.org/keywords/maximum-entropy-markov-model","display_name":"Maximum-entropy Markov model","score":0.563122034072876},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5438531041145325},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5112452507019043},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4465119242668152},{"id":"https://openalex.org/keywords/model-selection","display_name":"Model selection","score":0.4448803663253784},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43261459469795227},{"id":"https://openalex.org/keywords/variable-order-markov-model","display_name":"Variable-order Markov model","score":0.3054206967353821},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.2839099168777466},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.19038215279579163},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1672336757183075}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.880449652671814},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7969750165939331},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7485278844833374},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5970318913459778},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.5822001695632935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5773757696151733},{"id":"https://openalex.org/C196956702","wikidata":"https://www.wikidata.org/wiki/Q6795829","display_name":"Maximum-entropy Markov model","level":5,"score":0.563122034072876},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5438531041145325},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5112452507019043},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4465119242668152},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.4448803663253784},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43261459469795227},{"id":"https://openalex.org/C54907487","wikidata":"https://www.wikidata.org/wiki/Q7915688","display_name":"Variable-order Markov model","level":4,"score":0.3054206967353821},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.2839099168777466},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.19038215279579163},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1672336757183075}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icme.2003.1220857","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2003.1220857","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.128.5871","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.128.5871","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://labrosa.ee.columbia.edu/~dpwe/pubs/icme03-hmmsel.pdf","raw_type":"text"},{"id":"pmh:oai:academiccommons.columbia.edu:10.7916/D8H13BDP","is_oa":false,"landing_page_url":"https://doi.org/10.7916/D8H13BDP","pdf_url":null,"source":{"id":"https://openalex.org/S4306402601","display_name":"Columbia Academic Commons (Columbia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I78577930","host_organization_name":"Columbia University","host_organization_lineage":["https://openalex.org/I78577930"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Articles"},{"id":"doi:10.7916/d8h13bdp","is_oa":true,"landing_page_url":"https://doi.org/10.7916/d8h13bdp","pdf_url":null,"source":{"id":"https://openalex.org/S4306402601","display_name":"Columbia Academic Commons (Columbia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I78577930","host_organization_name":"Columbia University","host_organization_lineage":["https://openalex.org/I78577930"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.7916/d8h13bdp","is_oa":true,"landing_page_url":"https://doi.org/10.7916/d8h13bdp","pdf_url":null,"source":{"id":"https://openalex.org/S4306402601","display_name":"Columbia Academic Commons (Columbia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I78577930","host_organization_name":"Columbia University","host_organization_lineage":["https://openalex.org/I78577930"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W34562744","https://openalex.org/W1492282630","https://openalex.org/W1997527178","https://openalex.org/W2057613716","https://openalex.org/W2074188409","https://openalex.org/W2103203308","https://openalex.org/W2126281861","https://openalex.org/W2168175751","https://openalex.org/W2185457377","https://openalex.org/W2343867458","https://openalex.org/W3152454254","https://openalex.org/W6601432023","https://openalex.org/W6664934753"],"related_works":["https://openalex.org/W1615861041","https://openalex.org/W4313547211","https://openalex.org/W2147727120","https://openalex.org/W2799426416","https://openalex.org/W3113307220","https://openalex.org/W2032622457","https://openalex.org/W2082284720","https://openalex.org/W2056043311","https://openalex.org/W1840407238","https://openalex.org/W2048052024"],"abstract_inverted_index":{"Hidden":[0],"Markov":[1],"models":[2,63,156,185],"(HMMs)":[3],"permit":[4],"a":[5,51,91,99,131,146],"natural":[6,52,92],"and":[7,18,30,42,95,105,125],"flexible":[8],"way":[9],"to":[10,64,123],"model":[11,79],"time-sequential":[12],"data.":[13],"The":[14,155],"ease":[15],"of":[16,62,70,77,90,98,109,113,130,133,145,182,221],"concatenation":[17],"time-warping":[19],"algorithms":[20],"implementation":[21],"on":[22,45,85],"HMMs":[23,114],"suit":[24],"them":[25],"very":[26],"well":[27],"for":[28,202],"segmentation":[29],"content":[31],"based":[32,148],"audio":[33,136],"classification":[34,149,193,209],"applications,":[35],"as":[36,174,212],"is":[37],"clear":[38,100],"from":[39],"their":[40,188],"extended":[41],"successful":[43],"use":[44],"speech":[46,72],"recognition":[47],"applications.":[48],"Speech":[49],"has":[50],"basic":[53,93],"unit,":[54,94],"the":[55,60,71,75,78,88,96,103,106,127,143,152,175,183,191,199,203,218],"phone,":[56],"which":[57],"normally":[58],"delimits":[59],"number":[61],"one":[65],"per":[66],"phone.":[67],"Moreover,":[68],"knowledge":[69],"structure":[73],"facilitates":[74],"choice":[76],"parameters.":[80],"When":[81],"modeling":[82],"generic":[83,135],"audio,":[84],"other":[86],"hand,":[87],"lack":[89],"absence":[97],"structure,":[101],"make":[102],"selection":[104,171],"parameter":[107],"estimation":[108],"an":[110],"optimal":[111],"set":[112,132],"difficult.":[115],"In":[116],"this":[117],"paper":[118],"we":[119],"present":[120],"different":[121],"approaches":[122,141],"select":[124],"estimate":[126],"HMM":[128],"parameters":[129],"representative":[134],"classes.":[137],"We":[138],"compare":[139],"these":[140],"in":[142,190],"context":[144],"content-":[147],"application":[150],"using":[151],"MuscleFish":[153],"database.":[154],"are":[157],"first":[158],"found":[159],"through":[160],"frame":[161],"clustering":[162],"or":[163],"by":[164,206],"traditional":[165],"EM":[166],"techniques":[167],"under":[168],"some":[169],"specific":[170],"criteria,":[172],"such":[173,211],"Bayesian":[176],"information":[177],"criterion.":[178],"Further":[179],"discriminative":[180,208],"training":[181],"initial":[184],"considerably":[186],"improve":[187],"performance":[189],"content-based":[192],"task,":[194,205],"obtaining":[195],"results":[196],"comparable":[197],"with":[198],"ones":[200],"obtained,":[201],"same":[204],"inherently":[207],"methods,":[210],"support":[213],"vector":[214],"machines,":[215],"while":[216],"preserving":[217],"intrinsic":[219],"flexibility":[220],"HMMs.":[222]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}