{"id":"https://openalex.org/W2154875548","doi":"https://doi.org/10.1109/icassp.1987.1169481","title":"Duration modelling in finite state automata for speech recognition and fast speaker adaptation","display_name":"Duration modelling in finite state automata for speech recognition and fast speaker adaptation","publication_year":2005,"publication_date":"2005-03-24","ids":{"openalex":"https://openalex.org/W2154875548","doi":"https://doi.org/10.1109/icassp.1987.1169481","mag":"2154875548"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.1987.1169481","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1987.1169481","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP '87. IEEE International Conference on Acoustics, Speech, and Signal Processing","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/A5058780637","display_name":"M. Codogno","orcid":null},"institutions":[{"id":"https://openalex.org/I1298633626","display_name":"Telecom Italia Lab","ror":"https://ror.org/01rt74q71","country_code":"IT","type":"facility","lineage":["https://openalex.org/I1298633626","https://openalex.org/I137543953"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"M. Codogno","raw_affiliation_strings":["CSELT, Torino, Italy"],"affiliations":[{"raw_affiliation_string":"CSELT, Torino, Italy","institution_ids":["https://openalex.org/I1298633626"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027795080","display_name":"L. Fissore","orcid":null},"institutions":[{"id":"https://openalex.org/I1298633626","display_name":"Telecom Italia Lab","ror":"https://ror.org/01rt74q71","country_code":"IT","type":"facility","lineage":["https://openalex.org/I1298633626","https://openalex.org/I137543953"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"L. Fissore","raw_affiliation_strings":["CSELT, Torino, Italy"],"affiliations":[{"raw_affiliation_string":"CSELT, Torino, Italy","institution_ids":["https://openalex.org/I1298633626"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5058780637"],"corresponding_institution_ids":["https://openalex.org/I1298633626"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.1558077,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"12","issue":null,"first_page":"1269","last_page":"1272"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9972000122070312,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9940999746322632,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8028085827827454},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7785561084747314},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7272952198982239},{"id":"https://openalex.org/keywords/coarticulation","display_name":"Coarticulation","score":0.6109558939933777},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.5960832834243774},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.5035447478294373},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.4743669927120209},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4553107023239136},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.45283812284469604},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.45195192098617554},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44677096605300903},{"id":"https://openalex.org/keywords/automaton","display_name":"Automaton","score":0.4421892762184143},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4355737268924713}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8028085827827454},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7785561084747314},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7272952198982239},{"id":"https://openalex.org/C130727458","wikidata":"https://www.wikidata.org/wiki/Q1639109","display_name":"Coarticulation","level":3,"score":0.6109558939933777},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.5960832834243774},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.5035447478294373},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.4743669927120209},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4553107023239136},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.45283812284469604},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.45195192098617554},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44677096605300903},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.4421892762184143},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4355737268924713},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"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/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.1987.1169481","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1987.1169481","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP '87. IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1896748021","https://openalex.org/W1975352209","https://openalex.org/W2014089984","https://openalex.org/W2086699924","https://openalex.org/W2105080323","https://openalex.org/W2117515856"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1493012537","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W2175373321","https://openalex.org/W1521049138","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W1999004162","https://openalex.org/W4280634406"],"abstract_inverted_index":{"The":[0],"classical":[1],"first-order":[2],"Hidden":[3],"Markov":[4],"Models":[5],"with":[6,21,134],"continuous":[7,31],"probabilistic":[8],"density":[9,91],"function":[10],"(HMMCs)":[11],"seem":[12],"to":[13,23,46,59,76,95],"be":[14],"a":[15,38,74,121,126],"promising":[16],"tool":[17],"for":[18,125],"speech":[19,32],"modelling":[20],"reference":[22],"the":[24,48,53,83,97,117,135],"task":[25],"of":[26,79,99,119],"both":[27,100],"isolated":[28],"word":[29],"and":[30,129],"recognition.":[33],"However,":[34],"these":[35,131],"models":[36,80,133],"have":[37,108],"strong":[39],"limitation":[40],"because":[41],"they":[42],"are":[43,70],"poorly":[44],"able":[45],"capture":[47],"information":[49],"about":[50],"duration,":[51],"sometimes":[52],"most":[54],"important":[55],"feature":[56],"that":[57],"permits":[58],"distinguish":[60],"between":[61],"similar":[62],"sounds.":[63],"In":[64,93],"this":[65],"paper":[66],"two":[67,103],"different":[68],"approaches":[69],"exploited,":[71],"in":[72,81],"such":[73],"way":[75],"obtain":[77],"sets":[78],"which":[82],"state":[84],"duration":[85,132],"is":[86],"characterized":[87],"by":[88],"suited":[89],"probability":[90],"functions.":[92],"order":[94],"evaluate":[96],"performance":[98],"model":[101],"sets,":[102],"difficult":[104],"speaker-dependent":[105],"recognition":[106],"tasks":[107],"been":[109,114],"carried":[110],"out.":[111],"It":[112],"has":[113],"also":[115],"tested":[116],"opportunity":[118],"using":[120],"limited-size":[122],"training":[123],"lexicon":[124],"new":[127],"speaker,":[128],"merge":[130],"other":[136],"ones":[137],"obtained":[138],"through":[139],"some":[140],"speakers.":[141]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}