{"id":"https://openalex.org/W2548001695","doi":"https://doi.org/10.1109/nlpke.2011.6138246","title":"Phoneme set selection for russian speech recognition","display_name":"Phoneme set selection for russian speech recognition","publication_year":2011,"publication_date":"2011-11-01","ids":{"openalex":"https://openalex.org/W2548001695","doi":"https://doi.org/10.1109/nlpke.2011.6138246","mag":"2548001695"},"language":"en","primary_location":{"id":"doi:10.1109/nlpke.2011.6138246","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nlpke.2011.6138246","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 7th International Conference on Natural Language Processing and Knowledge Engineering","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/A5069801139","display_name":"Daria Vazhenina","orcid":null},"institutions":[{"id":"https://openalex.org/I141591182","display_name":"University of Aizu","ror":"https://ror.org/02pg0e883","country_code":"JP","type":"education","lineage":["https://openalex.org/I141591182"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Daria Vazhenina","raw_affiliation_strings":["Human Interface Laboratory, University of Aizu, Japan"],"affiliations":[{"raw_affiliation_string":"Human Interface Laboratory, University of Aizu, Japan","institution_ids":["https://openalex.org/I141591182"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039443541","display_name":"Konstantin Markov","orcid":"https://orcid.org/0000-0003-1838-4789"},"institutions":[{"id":"https://openalex.org/I141591182","display_name":"University of Aizu","ror":"https://ror.org/02pg0e883","country_code":"JP","type":"education","lineage":["https://openalex.org/I141591182"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Konstantin Markov","raw_affiliation_strings":["Human Interface Laboratory, University of Aizu, Japan"],"affiliations":[{"raw_affiliation_string":"Human Interface Laboratory, University of Aizu, Japan","institution_ids":["https://openalex.org/I141591182"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5069801139"],"corresponding_institution_ids":["https://openalex.org/I141591182"],"apc_list":null,"apc_paid":null,"fwci":4.7033,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.95119407,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9990000128746033,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.782178521156311},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7662577629089355},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6604620218276978},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.563792884349823},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5153409838676453},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5153048038482666},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5054717063903809},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46372339129447937},{"id":"https://openalex.org/keywords/confusion","display_name":"Confusion","score":0.4497529864311218},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4243812561035156},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4212878942489624},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.41727936267852783},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3755300045013428},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.23537707328796387},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13692530989646912}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.782178521156311},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7662577629089355},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6604620218276978},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.563792884349823},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5153409838676453},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5153048038482666},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5054717063903809},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46372339129447937},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.4497529864311218},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4243812561035156},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4212878942489624},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.41727936267852783},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3755300045013428},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.23537707328796387},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13692530989646912},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.0},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/nlpke.2011.6138246","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nlpke.2011.6138246","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 7th International Conference on Natural Language Processing and Knowledge Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W80018330","https://openalex.org/W163174961","https://openalex.org/W1553630706","https://openalex.org/W1992874062","https://openalex.org/W2089381378","https://openalex.org/W2125133735","https://openalex.org/W2142319389","https://openalex.org/W2167655920","https://openalex.org/W4285719527","https://openalex.org/W6603321232","https://openalex.org/W6648442429","https://openalex.org/W6681062664"],"related_works":["https://openalex.org/W3081187864","https://openalex.org/W151018310","https://openalex.org/W4380605396","https://openalex.org/W4298261218","https://openalex.org/W2008737763","https://openalex.org/W3151376046","https://openalex.org/W2584084702","https://openalex.org/W2784059283","https://openalex.org/W2105439218","https://openalex.org/W2291624303"],"abstract_inverted_index":{"In":[0,62],"this":[1,121],"paper,":[2],"we":[3,83,129,154],"describe":[4],"a":[5,86],"method":[6],"for":[7,22,48,58,187,193],"phoneme":[8,31,59,88,97,117,151,158,178,185,188],"set":[9,60,89,141,186],"selection":[10],"based":[11,105],"on":[12,106,149],"combination":[13],"of":[14,116,163],"phonological":[15],"and":[16,19,77,90,110,190],"statistical":[17,52],"information":[18],"its":[20],"application":[21],"Russian":[23,27,63,126],"speech":[24,145,196],"recognition.":[25,197],"For":[26],"language,":[28,64],"currently":[29],"used":[30,138],"sets":[32,159,173,179],"are":[33,180],"mostly":[34],"rule-based":[35],"or":[36,43,75,80],"heuristically":[37],"derived":[38,155],"from":[39,113],"the":[40,124,143,150,176,183],"standard":[41],"SAMPA":[42],"IPA":[44,125],"phonetic":[45,107,127],"alphabets.":[46],"However,":[47],"some":[49],"other":[50,157],"languages,":[51],"methods":[53],"have":[54],"been":[55],"found":[56],"useful":[57],"optimization.":[61],"almost":[65],"all":[66],"phonemes":[67,164],"come":[68],"in":[69,142],"pairs:":[70],"consonants":[71],"can":[72],"be":[73],"hard":[74],"soft":[76],"vowels":[78],"stressed":[79],"unstressed.":[81],"First,":[82],"start":[84],"with":[85,160],"big":[87],"then":[91],"gradually":[92],"reduce":[93],"it":[94,132],"by":[95],"merging":[96],"pairs.":[98],"Decision,":[99],"which":[100,136],"pair":[101],"to":[102,123,133,166],"merge,":[103],"is":[104],"pronunciation":[108],"rules":[109],"statistics":[111],"obtained":[112],"confusion":[114,152],"matrix":[115],"recognition":[118,169,189],"experiments.":[119],"Applying":[120],"approach":[122],"set,":[128],"first":[130],"reduced":[131,177],"47":[134],"phonemes,":[135],"were":[137],"as":[139,191],"initial":[140,184],"subsequent":[144],"model":[146],"training.":[147],"Based":[148],"results,":[153],"several":[156],"different":[161],"number":[162],"down":[165],"27.":[167],"Speech":[168],"experiments":[170],"using":[171],"these":[172],"showed":[174],"that":[175],"better":[181],"than":[182],"good":[192],"word":[194],"level":[195]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}