{"id":"https://openalex.org/W2397093049","doi":"https://doi.org/10.21437/interspeech.2011-190","title":"Effective triphone mapping for acoustic modeling in speech recognition","display_name":"Effective triphone mapping for acoustic modeling in speech recognition","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W2397093049","doi":"https://doi.org/10.21437/interspeech.2011-190","mag":"2397093049"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-190","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-190","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","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/A5078651630","display_name":"Sakhia Darjaa","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sakhia Darjaa","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003558571","display_name":"Milo\u0161 Cer\u0148ak","orcid":"https://orcid.org/0000-0002-5569-9491"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Milo\u0161 Cer\u0148ak","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057480095","display_name":"Mari\u00e1n Trnka","orcid":"https://orcid.org/0000-0002-2260-7757"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mari\u00e1n Trnka","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075303124","display_name":"Milan Rusko","orcid":"https://orcid.org/0000-0002-2036-7323"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Milan Rusko","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5038981603","display_name":"R\u00f3bert Sabo","orcid":"https://orcid.org/0000-0001-5587-1362"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"R\u00f3bert Sabo","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5078651630"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.4136,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.96619993,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1717","last_page":"1720"},"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":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.7401958107948303},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.708878219127655},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.47817546129226685},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.36596283316612244},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3303747773170471}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7401958107948303},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.708878219127655},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.47817546129226685},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.36596283316612244},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3303747773170471}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2011-190","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-190","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5699999928474426,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W17500809","https://openalex.org/W1481688629","https://openalex.org/W1502984613","https://openalex.org/W1841961279","https://openalex.org/W1979447841","https://openalex.org/W2021396747","https://openalex.org/W2033178790","https://openalex.org/W2096466030","https://openalex.org/W2143562645","https://openalex.org/W2151941172","https://openalex.org/W2158069733"],"related_works":["https://openalex.org/W2130717063","https://openalex.org/W2533508831","https://openalex.org/W2981428355","https://openalex.org/W2150288981","https://openalex.org/W4383605217","https://openalex.org/W1599055764","https://openalex.org/W2742699532","https://openalex.org/W48790062","https://openalex.org/W2149163000","https://openalex.org/W2131711534"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"effective":[3],"triphone":[4,74,98],"mapping":[5,99],"for":[6,61,128],"acoustic":[7,63],"models":[8,129],"training":[9],"in":[10,90],"automatic":[11],"speech":[12],"recognition,":[13],"which":[14],"allows":[15],"the":[16,107],"synthesis":[17],"of":[18,23,34,39,68,97,120],"unseen":[19],"triphones.":[20],"The":[21,47,87],"description":[22],"this":[24],"data-driven":[25],"model":[26],"clustering,":[27],"including":[28],"experiments":[29],"performed":[30],"using":[31],"350":[32],"hours":[33],"a":[35,66,73,82],"Slovak":[36],"audio":[37],"database":[38],"mixed":[40],"read":[41],"and":[42,56,71,133],"spontaneous":[43],"speech,":[44],"are":[45,110],"presented.":[46],"proposed":[48],"technique":[49],"is":[50,58,92],"compared":[51],"with":[52,102,114,130],"treebased":[53],"state":[54,84],"tying,":[55],"it":[57],"shown":[59],"that":[60],"bigger":[62],"models,":[64],"at":[65,140],"size":[67],"4000":[69],"states":[70],"more,":[72],"mapped":[75],"HMM":[76],"system":[77],"achieves":[78],"better":[79,112],"performance":[80,91],"than":[81,113],"tree-based":[83],"tying":[85],"system.":[86],"main":[88],"gain":[89,139],"due":[93],"to":[94,135],"latent":[95],"application":[96],"on":[100],"monophones":[101],"multiple":[103],"Gaussian":[104],"pdfs,":[105],"so":[106],"cloned":[108],"triphones":[109],"initialized":[111],"single":[115],"Gaussians":[116],"monophones.":[117],"Absolute":[118],"decrease":[119],"word":[121],"error":[122],"rate":[123],"was":[124],"0.46%":[125],"(5.73%":[126],"relatively)":[127,138],"7500":[131],"states,":[132],"decreased":[134],"0.4%":[136],"(5.17%":[137],"11500":[141],"states.":[142]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}