{"id":"https://openalex.org/W133585348","doi":"https://doi.org/10.21437/eurospeech.1997-59","title":"HMM state clustering across allophone class boundaries","display_name":"HMM state clustering across allophone class boundaries","publication_year":1997,"publication_date":"1997-09-22","ids":{"openalex":"https://openalex.org/W133585348","doi":"https://doi.org/10.21437/eurospeech.1997-59","mag":"133585348"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.1997-59","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1997-59","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th European Conference on Speech Communication and Technology (Eurospeech 1997)","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/A5016276775","display_name":"Ze\u2019ev Rivlin","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ze'ev Rivlin","raw_affiliation_strings":["SRI, International;"],"affiliations":[{"raw_affiliation_string":"SRI, International;","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104349809","display_name":"Ananth Sankar","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ananth Sankar","raw_affiliation_strings":["SRI, International;"],"affiliations":[{"raw_affiliation_string":"SRI, International;","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051405063","display_name":"Harry Bratt","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harry Bratt","raw_affiliation_strings":["SRI, International;"],"affiliations":[{"raw_affiliation_string":"SRI, International;","institution_ids":["https://openalex.org/I1298353152"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5016276775"],"corresponding_institution_ids":["https://openalex.org/I1298353152"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.0200791,"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":"127","last_page":"130"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9975000023841858,"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/T11309","display_name":"Music and Audio Processing","score":0.9930999875068665,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8370944261550903},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.8159172534942627},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7544474601745605},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5793911218643188},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5562788248062134},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5499264597892761},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.525858461856842},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4579947590827942},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4501205086708069},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33751991391181946},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.062321990728378296}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8370944261550903},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8159172534942627},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7544474601745605},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5793911218643188},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5562788248062134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5499264597892761},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.525858461856842},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4579947590827942},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4501205086708069},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33751991391181946},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.062321990728378296},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/eurospeech.1997-59","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1997-59","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th European Conference on Speech Communication and Technology (Eurospeech 1997)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.48.8503","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.48.8503","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ftp://ftp.speech.sri.com/pub/papers/eurospeech.97.zev.ps","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1586645951","https://openalex.org/W1978094888","https://openalex.org/W1986695354","https://openalex.org/W2050597349","https://openalex.org/W2098773974","https://openalex.org/W2122028591","https://openalex.org/W2139884663","https://openalex.org/W2479014774"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2025614924","https://openalex.org/W2294335174","https://openalex.org/W2097963413","https://openalex.org/W3145575561","https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W2160650576","https://openalex.org/W1578916557"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,66,75],"novel":[3],"approach":[4,50],"to":[5,57],"hidden":[6],"Markov":[7],"model":[8],"(HMM)":[9],"state":[10,63,83],"clustering":[11,84,106,123],"based":[12,32],"on":[13,33],"the":[14,44,72,81,86,105,115],"use":[15,39],"of":[16,68,74,107],"broad":[17,130],"phone":[18,36,131],"classes":[19,140],"and":[20],"an":[21],"allophone":[22,95,110,125,139,146],"class":[23,111,126],"entropy":[24],"measure.":[25],"Most":[26],"state-of-the-art":[27],"largevocabulary":[28],"speech":[29],"recognizers":[30],"are":[31,89,117],"context-dependent":[34],"(CD)":[35],"HMMs":[37],"that":[38],"Gaussian":[40,76],"mixture":[41,77],"models":[42],"for":[43,51],"state-conditioned":[45],"observation":[46],"densities.":[47],"A":[48],"common":[49],"robust":[52],"HMM":[53,59,87],"parameter":[54],"estimation":[55],"is":[56],"cluster":[58,64],"states":[60,88,108,116,136],"where":[61],"each":[62],"shares":[65],"set":[67],"parameters":[69],"such":[70],"as":[71],"components":[73],"model.":[78],"In":[79],"all":[80],"current":[82],"algorithms,":[85],"clustered":[90,143],"only":[91],"within":[92,133],"their":[93],"respective":[94],"classes.":[96],"While":[97],"this":[98],"makes":[99],"some":[100],"intuitive":[101],"sense,":[102],"it":[103],"prevents":[104],"across":[109,124],"boundaries,":[112],"even":[113],"when":[114],"acoustically":[118],"similar.":[119],"Our":[120],"algorithm":[121],"allows":[122],"boundaries":[127],"by":[128],"defining":[129],"groups":[132],"which":[134],"two":[135],"from":[137],"different":[138],"can":[141],"be":[142],"together.":[144],"An":[145],"...":[147]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}