{"id":"https://openalex.org/W2132188400","doi":"https://doi.org/10.1109/icassp.2012.6289026","title":"CRF-based confidence measures of recognized candidates for lattice-based audio indexing","display_name":"CRF-based confidence measures of recognized candidates for lattice-based audio indexing","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2132188400","doi":"https://doi.org/10.1109/icassp.2012.6289026","mag":"2132188400"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6289026","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6289026","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5010173604","display_name":"Zhijian Ou","orcid":"https://orcid.org/0000-0002-9018-5074"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijian Ou","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China","Department of Electronic Engineering, Tsinghua University, Beijing, CHINA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, CHINA#TAB#","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040757997","display_name":"Huaqing Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaqing Luo","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China","Department of Electronic Engineering, Tsinghua University, Beijing, CHINA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, CHINA#TAB#","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4933","last_page":"4936"},"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/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9994999766349792,"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/crfs","display_name":"CRFS","score":0.9031045436859131},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.8038730025291443},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.7460654377937317},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7224734425544739},{"id":"https://openalex.org/keywords/lattice","display_name":"Lattice (music)","score":0.6438794136047363},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5595744252204895},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.4707508683204651},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.37892043590545654},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3469748795032501},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3402813673019409},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32291561365127563}],"concepts":[{"id":"https://openalex.org/C2775953691","wikidata":"https://www.wikidata.org/wiki/Q5013874","display_name":"CRFS","level":3,"score":0.9031045436859131},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.8038730025291443},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.7460654377937317},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7224734425544739},{"id":"https://openalex.org/C2781204021","wikidata":"https://www.wikidata.org/wiki/Q6497091","display_name":"Lattice (music)","level":2,"score":0.6438794136047363},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5595744252204895},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.4707508683204651},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.37892043590545654},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3469748795032501},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3402813673019409},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32291561365127563},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2012.6289026","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6289026","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1606054028","https://openalex.org/W2034537249","https://openalex.org/W2125937262","https://openalex.org/W2127914268","https://openalex.org/W2134659216","https://openalex.org/W2147880316","https://openalex.org/W2167556823","https://openalex.org/W2594610113","https://openalex.org/W6636107938","https://openalex.org/W6682082992","https://openalex.org/W6684666846"],"related_works":["https://openalex.org/W50079190","https://openalex.org/W2356597680","https://openalex.org/W182104056","https://openalex.org/W2111726165","https://openalex.org/W2011251309","https://openalex.org/W3108423214","https://openalex.org/W2796133761","https://openalex.org/W3088215229","https://openalex.org/W2511246383","https://openalex.org/W2184553228"],"abstract_inverted_index":{"The":[0],"use":[1],"of":[2],"forward-backward":[3],"(FB)":[4],"computation":[5],"based":[6],"posterior":[7,100],"probabilities":[8,101],"as":[9,76,87],"confidence":[10],"measures":[11],"(CMs)":[12],"for":[13,41,145,159],"all":[14],"recognized":[15],"candidates":[16],"in":[17,72,134,142,162],"a":[18,31,53,77,122],"lattice":[19,74,136,164],"seems":[20],"to":[21,68,112],"be":[22,44,103],"common":[23],"across":[24],"various":[25,94],"lattice-based":[26,167],"audio":[27,168],"indexing":[28],"systems.":[29],"However,":[30],"major":[32],"limitation":[33],"with":[34],"this":[35,64,92],"approach":[36,154],"is":[37],"that":[38,107],"its":[39],"performance":[40,157],"CMs":[42,71,144,161],"cannot":[43],"improved":[45],"easily,":[46],"since":[47],"it":[48],"relies":[49],"almost":[50],"entirely":[51],"on":[52],"single":[54],"information":[55],"source":[56],"-":[57],"the":[58,73,88,98,135,146,152,163],"acoustic":[59],"and":[60,116,166],"language-model":[61],"probabilities.":[62],"In":[63,91],"paper,":[65],"we":[66,129],"propose":[67],"formulate":[69],"computing":[70],"case":[75,165],"multi-class":[78],"sequential":[79],"labeling":[80],"problem,":[81],"using":[82],"conditional":[83],"random":[84],"fields":[85],"(CRFs)":[86],"underlying":[89],"model.":[90],"approach,":[93],"relevant":[95],"features":[96,118],"including":[97],"FB":[99],"could":[102],"combined":[104],"together.":[105],"Note":[106],"CRFs":[108],"are":[109,119],"well":[110],"suited":[111],"label":[113],"sequence":[114],"data":[115],"some":[117],"defined":[120],"over":[121],"word":[123],"sequence.":[124],"This":[125],"paper":[126],"presents":[127],"how":[128],"resolve":[130],"these":[131],"two":[132],"issues":[133],"case,":[137],"beyond":[138],"others'":[139],"previous":[140],"work":[141],"CRF-based":[143],"1-best":[147],"case.":[148],"Once":[149],"properly":[150],"implemented,":[151],"proposed":[153],"achieves":[155],"significant":[156],"improvements":[158],"both":[160],"indexing.":[169]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}