{"id":"https://openalex.org/W2154369589","doi":"https://doi.org/10.1109/icassp.2004.1327106","title":"Automatic and language independent triphone training using phonetic tables [speech recognition]","display_name":"Automatic and language independent triphone training using phonetic tables [speech recognition]","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2154369589","doi":"https://doi.org/10.1109/icassp.2004.1327106","mag":"2154369589"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1327106","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1327106","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","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/A5087163988","display_name":"Lorin Netsch","orcid":null},"institutions":[{"id":"https://openalex.org/I74760111","display_name":"Texas Instruments (United States)","ror":"https://ror.org/03vsmv677","country_code":"US","type":"company","lineage":["https://openalex.org/I74760111"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"L. Netsch","raw_affiliation_strings":["Texas Instruments, Inc., Dallas, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas Instruments, Inc., Dallas, TX, USA","institution_ids":["https://openalex.org/I74760111"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075072276","display_name":"Alexis Bernard","orcid":"https://orcid.org/0009-0002-2834-6540"},"institutions":[{"id":"https://openalex.org/I74760111","display_name":"Texas Instruments (United States)","ror":"https://ror.org/03vsmv677","country_code":"US","type":"company","lineage":["https://openalex.org/I74760111"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A. Bernard","raw_affiliation_strings":["Texas Instruments, Inc., Dallas, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas Instruments, Inc., Dallas, TX, USA","institution_ids":["https://openalex.org/I74760111"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74760111"],"apc_list":null,"apc_paid":null,"fwci":0.2205,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.50068874,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"5","issue":null,"first_page":"V","last_page":"297"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9995999932289124,"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":0.9980000257492065,"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/computer-science","display_name":"Computer science","score":0.860491931438446},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.7585787177085876},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7528464198112488},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6986074447631836},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5379761457443237},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.48783138394355774},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47825613617897034},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4407527446746826},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4318111538887024},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.41992297768592834},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.41548746824264526},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39170539379119873},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3645022511482239},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3121250867843628},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.0743609070777893}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.860491931438446},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7585787177085876},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7528464198112488},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6986074447631836},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5379761457443237},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.48783138394355774},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47825613617897034},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4407527446746826},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4318111538887024},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.41992297768592834},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.41548746824264526},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39170539379119873},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3645022511482239},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3121250867843628},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.0743609070777893},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2004.1327106","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1327106","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1555037511","https://openalex.org/W2108341231","https://openalex.org/W2171761326","https://openalex.org/W4402490925","https://openalex.org/W6871885761"],"related_works":["https://openalex.org/W1566315437","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2594897229","https://openalex.org/W4290708361","https://openalex.org/W2050138804","https://openalex.org/W767271433","https://openalex.org/W2126322296","https://openalex.org/W2244609359","https://openalex.org/W2141404479"],"abstract_inverted_index":{"Training":[0],"triphone":[1,68,110],"acoustic":[2],"models":[3,111],"for":[4,45,123],"speech":[5],"recognition":[6,90,102],"is":[7,40,105],"time-consuming":[8],"and":[9,70],"requires":[10],"important":[11],"manual":[12,125],"intervention.":[13],"We":[14],"present":[15],"an":[16,49],"alternative":[17],"solution,":[18],"performing":[19,62],"automatic":[20,75],"training":[21,72,79],"by":[22,60],"use":[23],"of":[24,34,52,65,77],"a":[25,99,113,119],"pronunciation":[26],"phonetic":[27],"table":[28],"which":[29,86],"summarizes":[30],"the":[31,35,63,78],"articulatory":[32],"characteristics":[33],"target":[36],"language.":[37],"The":[38,74],"method":[39],"able":[41],"to":[42,83,94,118],"train":[43],"triphones":[44],"any":[46],"language,":[47],"given":[48],"existing":[50],"set":[51],"reference":[53],"monophones":[54],"in":[55],"one":[56],"or":[57],"more":[58],"languages,":[59],"automatically":[61,108],"tasks":[64],"monophone":[66],"seeding,":[67],"clustering":[69],"other":[71],"steps.":[73],"nature":[76],"algorithm":[80],"lends":[81],"itself":[82],"parameter":[84],"optimization,":[85],"can":[87],"further":[88],"improve":[89],"accuracy":[91],"with":[92],"respect":[93],"manually":[95],"trained":[96],"models.":[97],"In":[98],"continuous":[100],"digit":[101],"experiment,":[103],"it":[104],"shown":[106],"that":[107],"generated":[109],"gave":[112],"1.26%":[114],"error":[115,121],"rate,":[116],"compared":[117],"2.30%":[120],"rate":[122],"its":[124],"counterpart.":[126]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}