{"id":"https://openalex.org/W2004752681","doi":"https://doi.org/10.1109/iihmsp.2007.4457488","title":"Audio-Visual Speech Recognition with Weighted KNN-based Classification in Mandarin Database","display_name":"Audio-Visual Speech Recognition with Weighted KNN-based Classification in Mandarin Database","publication_year":2007,"publication_date":"2007-11-01","ids":{"openalex":"https://openalex.org/W2004752681","doi":"https://doi.org/10.1109/iihmsp.2007.4457488","mag":"2004752681"},"language":"en","primary_location":{"id":"doi:10.1109/iihmsp.2007.4457488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iihmsp.2007.4457488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Third International Conference on Intelligent Information Hiding and Multimedia Signal Processing (IIH-MSP 2007)","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/A5040187372","display_name":"Tsang-Long Pao","orcid":null},"institutions":[{"id":"https://openalex.org/I65196183","display_name":"Tatung University","ror":"https://ror.org/030m18266","country_code":"TW","type":"education","lineage":["https://openalex.org/I65196183"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tsang-Long Pao","raw_affiliation_strings":["Department of Computer Science and Engineering, Tatung University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Tatung University, Taipei, Taiwan","institution_ids":["https://openalex.org/I65196183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027271308","display_name":"Wenyuan Liao","orcid":"https://orcid.org/0000-0002-6566-9341"},"institutions":[{"id":"https://openalex.org/I65196183","display_name":"Tatung University","ror":"https://ror.org/030m18266","country_code":"TW","type":"education","lineage":["https://openalex.org/I65196183"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wen-Yuan Liao","raw_affiliation_strings":["Department of Computer Science and Engineering, Tatung University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Tatung University, Taipei, Taiwan","institution_ids":["https://openalex.org/I65196183"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090617126","display_name":"Yu-Te Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I65196183","display_name":"Tatung University","ror":"https://ror.org/030m18266","country_code":"TW","type":"education","lineage":["https://openalex.org/I65196183"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Te Chen","raw_affiliation_strings":["Department of Computer Science and Engineering, Tatung University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Tatung University, Taipei, Taiwan","institution_ids":["https://openalex.org/I65196183"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.08929099,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"39","last_page":"42"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.995199978351593,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9898999929428101,"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":0.8284338712692261},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.7115603089332581},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7076596617698669},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.61487877368927},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5924805402755737},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5317396521568298},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5165228247642517},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.43638911843299866},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43394210934638977},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.41907623410224915},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.41094720363616943},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.36710119247436523},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.22568485140800476},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.07133671641349792}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8284338712692261},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.7115603089332581},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7076596617698669},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.61487877368927},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5924805402755737},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5317396521568298},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5165228247642517},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.43638911843299866},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43394210934638977},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.41907623410224915},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.41094720363616943},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.36710119247436523},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.22568485140800476},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.07133671641349792},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iihmsp.2007.4457488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iihmsp.2007.4457488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Third International Conference on Intelligent Information Hiding and Multimedia Signal Processing (IIH-MSP 2007)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W34667995","https://openalex.org/W1563622701","https://openalex.org/W1576996184","https://openalex.org/W2083792893","https://openalex.org/W2130695501","https://openalex.org/W2132999255","https://openalex.org/W2146614494","https://openalex.org/W2166835904","https://openalex.org/W6671432306"],"related_works":["https://openalex.org/W3159882232","https://openalex.org/W4241650944","https://openalex.org/W4243125559","https://openalex.org/W1541790149","https://openalex.org/W4241778367","https://openalex.org/W2752054555","https://openalex.org/W2527828870","https://openalex.org/W2184127972","https://openalex.org/W4214489098","https://openalex.org/W46679383"],"abstract_inverted_index":{"Automatic":[0],"speech":[1],"recognition":[2,33],"(ASR)":[3],"by":[4,36],"machine":[5],"has":[6,23],"been":[7,24],"a":[8,121],"goal":[9],"and":[10,59,115,127],"an":[11],"attractive":[12,26],"research":[13,27],"area":[14],"for":[15,29,72,75,134],"past":[16],"several":[17],"decades.":[18],"In":[19,82],"recent":[20],"years,":[21],"there":[22],"growing":[25],"topic":[28],"overcoming":[30],"certain":[31],"audio-only":[32,65],"problems.":[34],"Motivated":[35],"the":[37,42,56,70,73,76,80],"multimodal":[38],"nature":[39],"of":[40,79],"speech,":[41],"visual":[43,77],"feature":[44,78],"is":[45],"considered":[46],"to":[47,95,101],"bring":[48],"in":[49,55,91,125],"information":[50],"that":[51],"dose":[52],"not":[53],"existing":[54],"acoustic":[57],"signal":[58],"enables":[60],"improved":[61],"system":[62],"performance":[63],"over":[64],"methods.":[66],"We":[67,118,129],"first":[68],"introduce":[69],"method":[71],"extraction":[74],"lip.":[81],"this":[83,132],"paper,":[84],"we":[85],"compare":[86],"three":[87],"different":[88],"weighting":[89],"functions":[90],"weighted":[92,113,116],"KNN-based":[93],"classifiers":[94,108],"recognize":[96],"ten":[97],"digits,":[98],"including":[99],"0":[100],"9,":[102],"from":[103],"Mandarin":[104],"audio-visual":[105,123],"speech.":[106],"The":[107],"studied":[109],"include":[110],"traditional":[111],"KNN,":[112,114],"D-KNN.":[117],"also":[119],"create":[120],"new":[122],"database":[124,133],"English":[126],"Mandarin.":[128],"will":[130],"test":[131],"our":[135],"proposed":[136],"system,":[137],"with":[138],"some":[139],"experimental":[140],"results.":[141]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}