{"id":"https://openalex.org/W2403081842","doi":"https://doi.org/10.21437/eurospeech.1999-132","title":"Pronunciation modeling by sharing gaussian densities across phonetic models","display_name":"Pronunciation modeling by sharing gaussian densities across phonetic models","publication_year":1999,"publication_date":"1999-09-05","ids":{"openalex":"https://openalex.org/W2403081842","doi":"https://doi.org/10.21437/eurospeech.1999-132","mag":"2403081842"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.1999-132","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1999-132","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"6th European Conference on Speech Communication and Technology","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/A5055086464","display_name":"Murat Sara\u00e7lar","orcid":"https://orcid.org/0000-0002-7435-8510"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Murat Saraclar","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108291571","display_name":"Harriet J. Nock","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Harriet Nock","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5055086464"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.00395102,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.89289487,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"515","last_page":"518"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983999729156494,"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":0.9983999729156494,"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":0.9830999970436096,"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/T11309","display_name":"Music and Audio Processing","score":0.9502999782562256,"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/pronunciation","display_name":"Pronunciation","score":0.9357097148895264},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8095977306365967},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.784828245639801},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7526749968528748},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.6319097876548767},{"id":"https://openalex.org/keywords/phonetic-transcription","display_name":"Phonetic transcription","score":0.5249702334403992},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49371060729026794},{"id":"https://openalex.org/keywords/realization","display_name":"Realization (probability)","score":0.47050827741622925},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.44811397790908813},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4340599477291107},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36999082565307617},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3134390711784363},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1520746350288391},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1166788637638092}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.9357097148895264},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8095977306365967},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.784828245639801},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7526749968528748},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.6319097876548767},{"id":"https://openalex.org/C2777853878","wikidata":"https://www.wikidata.org/wiki/Q743569","display_name":"Phonetic transcription","level":2,"score":0.5249702334403992},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49371060729026794},{"id":"https://openalex.org/C2781089630","wikidata":"https://www.wikidata.org/wiki/Q21856745","display_name":"Realization (probability)","level":2,"score":0.47050827741622925},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.44811397790908813},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4340599477291107},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36999082565307617},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3134390711784363},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1520746350288391},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1166788637638092},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/eurospeech.1999-132","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1999-132","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"6th European Conference on Speech Communication and Technology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3114261385","https://openalex.org/W2917843404","https://openalex.org/W2473907094","https://openalex.org/W3084036048","https://openalex.org/W116351045","https://openalex.org/W1889898471","https://openalex.org/W2611159122","https://openalex.org/W1560466321","https://openalex.org/W2741500372","https://openalex.org/W2126322296"],"abstract_inverted_index":{"Conversational":[0],"speech":[1,20],"exhibits":[2],"considerable":[3],"pronunciation":[4,29,47,62,149],"variability,":[5],"which":[6,199],"has":[7],"been":[8,24],"shown":[9,88],"to":[10,27,37,53,70,80,133,150,174,193],"have":[11,23],"a":[12,134,144,156,195,221],"detrimental":[13],"effect":[14],"on":[15,110,124,228],"the":[16,32,59,75,92,95,111,147,161,168,180,184,187,229],"accuracy":[17,93,227],"of":[18,34,46,61,78,94,104,128,137,155,167,183,186],"automatic":[19],"recognition.":[21,71],"There":[22],"many":[25],"attempts":[26],"model":[28,66,101,164,170,216],"variation,":[30],"including":[31],"use":[33,77],"decision":[35,197],"trees":[36],"generate":[38],"alternate":[39,159,188],"word":[40],"pronunciations":[41,82],"from":[42],"phonemic":[43],"baseforms.":[44,126],"Use":[45],"models":[48,63,108,122],"during":[49],"recognition":[50,119,226],"is":[51,87,103,202,210,232],"known":[52],"improve":[54],"accuracy.":[55],"This":[56],"paper":[57],"describes":[58],"incorporation":[60],"into":[64],"acoustic":[65,100,121,215],"training":[67,102,217],"in":[68,74,117,146,225],"addition":[69],"Subtle":[72],"difficulties":[73],"straightforward":[76],"alternatives":[79],"canonical":[81,125,148],"are":[83,171],"first":[84],"illustrated:":[85],"it":[86],"that":[89,207],"simply":[90],"improving":[91],"phonetic":[96,114],"transcription":[97],"used":[98],"for":[99,214,218],"little":[105],"benefit.":[106],"Acoustic":[107],"trained":[109,123],"most":[112],"accurate":[113],"transcriptions":[115],"result":[116,131],"worse":[118],"than":[120,142],"Analysis":[127],"this":[129,191,208],"counterintuitive":[130],"leads":[132],"new":[135],"method":[136,209],"accommodating":[138],"nonstandard":[139],"pronunciations:":[140],"rather":[141],"allowing":[143],"phoneme":[145],"be":[151],"realized":[152],"as":[153],"one":[154],"few":[157],"distinct":[158],"phones,":[160],"hidden":[162],"Markov":[163],"(HMM)":[165],"states":[166,182],"phoneme?s":[169],"instead":[172],"allowed":[173],"share":[175],"Gaussian":[176],"mixture":[177],"components":[178],"with":[179],"HMM":[181],"model(s)":[185],"realization(s).":[189],"Qualitatively,":[190],"amounts":[192],"making":[194],"soft":[196],"about":[198],"surface":[200],"form":[201],"realized.":[203],"Quantitatively,":[204],"experiments":[205],"show":[206],"particularly":[211],"well":[212],"suited":[213],"spontaneous":[219],"speech:":[220],"1.7":[222],"%(absolute)":[223],"improvement":[224],"Switchboard":[230],"corpus":[231],"presented.":[233]},"counts_by_year":[{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}