{"id":"https://openalex.org/W147695644","doi":"https://doi.org/10.21437/interspeech.2004-261","title":"Context dependent \"long units\" for speech recognition","display_name":"Context dependent \"long units\" for speech recognition","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W147695644","doi":"https://doi.org/10.21437/interspeech.2004-261","mag":"147695644"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-261","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-261","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","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/A5030903462","display_name":"Denis Jouvet","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Denis Jouvet","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5065108094","display_name":"Ronaldo Messina","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ronaldo Messina","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"645","last_page":"648"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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":0.9983999729156494,"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/coarticulation","display_name":"Coarticulation","score":0.8794980049133301},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8047128915786743},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.735090434551239},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.732992947101593},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.6837014555931091},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.593125581741333},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5634928941726685},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.5172598958015442},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.44895118474960327},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43578171730041504},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3693455457687378},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07847249507904053},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.07620632648468018}],"concepts":[{"id":"https://openalex.org/C130727458","wikidata":"https://www.wikidata.org/wiki/Q1639109","display_name":"Coarticulation","level":3,"score":0.8794980049133301},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8047128915786743},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.735090434551239},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.732992947101593},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.6837014555931091},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.593125581741333},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5634928941726685},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.5172598958015442},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.44895118474960327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43578171730041504},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3693455457687378},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07847249507904053},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.07620632648468018},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2004-261","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-261","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W17921661","https://openalex.org/W172013813","https://openalex.org/W1493946344","https://openalex.org/W1510806122","https://openalex.org/W2121464381","https://openalex.org/W2167200294","https://openalex.org/W2497664846"],"related_works":["https://openalex.org/W2047235756","https://openalex.org/W2355417428","https://openalex.org/W3304542","https://openalex.org/W196866866","https://openalex.org/W2119371555","https://openalex.org/W2391432493","https://openalex.org/W2063670285","https://openalex.org/W2169455968","https://openalex.org/W2061937230","https://openalex.org/W2154156780"],"abstract_inverted_index":{"It":[0],"is":[1,42,65,78,137,142],"expected":[2],"that":[3,88],"longer-than-phoneme":[4],"units":[5,11,28,71],"such":[6,19],"as":[7,20],"syllables":[8],"or":[9,23],"multi-phone":[10,107],"can":[12],"deal":[13],"with":[14],"sources":[15],"of":[16,34,37,48,51,127,133],"performance":[17],"degradation,":[18],"pronunciation":[21],"variation":[22],"coarticulation,":[24],"better":[25],"than":[26],"phoneme-sized":[27],"like":[29],"triphones.":[30],"The":[31],"possible":[32],"number":[33,50],"contextual":[35],"realizations":[36],"those":[38],"\u201clong":[39],"units\u201d":[40],"(LU)":[41],"very":[43],"high,":[44],"causing":[45],"an":[46,134],"explosion":[47],"the":[49,57,62,138],"parameters":[52,68,118],"to":[53,66,72,80,116,129,145],"be":[54],"estimated.":[55],"As":[56],"training":[58,93],"data":[59],"are":[60],"limited,":[61],"usual":[63],"solution":[64],"share":[67,117],"between":[69,119],"different":[70,120],"improve":[73],"parameter":[74],"estimation.":[75],"Another":[76],"problem":[77],"how":[79],"provide":[81],"a":[82,85,111,125,146],"model":[83],"for":[84],"unit":[86],"(syllable/multiphones)":[87],"was":[89],"not":[90],"present":[91],"during":[92],"(unseen":[94],"unit).":[95],"In":[96],"this":[97],"paper":[98],"we":[99,123],"evaluate":[100],"and":[101,104,122],"compare":[102],"syllable":[103,136],"automatically":[105],"derived":[106],"units.":[108],"We":[109],"introduce":[110],"method":[112],"called":[113],"\u201ccontextual":[114],"factorization\u201d":[115],"models":[121],"propose":[124],"figure":[126],"merit":[128],"decide":[130],"which":[131],"decomposition":[132],"unseen":[135],"most":[139],"appropriate.":[140],"Performance":[141],"improved":[143],"comparing":[144],"triphone":[147],"based":[148],"system.":[149]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
