{"id":"https://openalex.org/W20830177","doi":"https://doi.org/10.21437/icslp.2000-450","title":"Frame level likelihood transformations for ASR and utterance verification","display_name":"Frame level likelihood transformations for ASR and utterance verification","publication_year":2000,"publication_date":"2000-10-16","ids":{"openalex":"https://openalex.org/W20830177","doi":"https://doi.org/10.21437/icslp.2000-450","mag":"20830177"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.2000-450","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2000-450","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"6th International Conference on Spoken Language Processing (ICSLP 2000)","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/A5039443541","display_name":"Konstantin Markov","orcid":"https://orcid.org/0000-0003-1838-4789"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Konstantin P. Markov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00234968,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"vol. 2, 1038","last_page":"1041"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980000257492065,"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":0.9980000257492065,"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":0.9948999881744385,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9847000241279602,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/timit","display_name":"TIMIT","score":0.7763663530349731},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7740623950958252},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7518700957298279},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7088471055030823},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7029491662979126},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6556028127670288},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6133548021316528},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5373996496200562},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49947404861450195},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4515697658061981},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2382521629333496}],"concepts":[{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.7763663530349731},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7740623950958252},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7518700957298279},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7088471055030823},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7029491662979126},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6556028127670288},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6133548021316528},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5373996496200562},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49947404861450195},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4515697658061981},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2382521629333496},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/icslp.2000-450","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2000-450","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"6th International Conference on Spoken Language Processing (ICSLP 2000)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W2086267546","https://openalex.org/W2135936685"],"related_works":["https://openalex.org/W80423236","https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W3134920593","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W2501000458","https://openalex.org/W1578749070","https://openalex.org/W2146842779","https://openalex.org/W2340308015"],"abstract_inverted_index":{"In":[0,39,130],"most":[1],"of":[2,20,27,53,60,68,89,126,147,153],"the":[3,28,32,36,51,54,66,100,127,170,178,183],"current":[4],"speech":[5],"recognition":[6,121,140,160,179],"systems":[7],"based":[8],"on":[9],"HMM,":[10],"existing":[11],"decoding":[12],"and":[13,35,46,99,122,141,144,150,161,181],"utterance":[14],"veri":[15,123,142,162,184],"cation":[16,124,143,185],"methods":[17],"make":[18],"use":[19],"state":[21,78],"output":[22],"likelihood":[23,67,97,172],"as":[24,112],"a":[25,44,145,151],"measure":[26],"acoustic":[29,37,55,70,114],"match":[30,56],"between":[31],"input":[33],"data":[34],"models.":[38],"this":[40,61],"paper,":[41],"we":[42,134,166],"present":[43],"new":[45,113],"more":[47],"generalized":[48],"approach":[49,62],"to":[50,64,74,80,189],"formation":[52],"score.":[57],"The":[58,93,109,164],"essence":[59],"is":[63],"transform":[65],"each":[69],"vector":[71],"with":[72],"respect":[73],"any":[75],"particular":[76],"HMM":[77],"according":[79],"some":[81],"non-linear":[82],"function.":[83],"We":[84],"have":[85],"investigated":[86],"two":[87],"types":[88],"such":[90],"transformation":[91],"functions.":[92],"rst":[94],"one,":[95],"performs":[96],"normalization,":[98],"second":[101],"one":[102],"transforms":[103],"likelihoods":[104],"into":[105],"exponentially":[106],"ordered":[107],"weights.":[108],"transformed":[110,171],"likelihoods,":[111],"scores,":[115,173],"are":[116],"used":[117,135],"further":[118],"for":[119,138,157],"decoding,":[120],"instead":[125],"conventional":[128],"likelihoods.":[129],"our":[131],"evaluation":[132],"experiments":[133],"TIMIT":[136],"database":[137,146],"phoneme":[139],"710":[148],"speakers":[149],"total":[152],"4252":[154],"distinct":[155],"words,":[156],"isolated":[158],"word":[159],"cation.":[163],"results":[165],"achieved":[167],"show":[168],"that":[169],"in":[174],"average,":[175],"increase":[176],"slightly":[177],"accuracy":[180],"reduce":[182],"error":[186],"rates":[187],"up":[188],"30%.":[190]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}