{"id":"https://openalex.org/W3016059848","doi":"https://doi.org/10.1109/icassp40776.2020.9053190","title":"Detecting Mismatch Between Text Script and Voice-Over Using Utterance Verification Based on Phoneme Recognition Ranking","display_name":"Detecting Mismatch Between Text Script and Voice-Over Using Utterance Verification Based on Phoneme Recognition Ranking","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016059848","doi":"https://doi.org/10.1109/icassp40776.2020.9053190","mag":"3016059848"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053190","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053190","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5018321415","display_name":"Yoonjae Jeong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210135449","display_name":"NCSOFT (South Korea)","ror":"https://ror.org/03q4mza74","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210135449"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Yoonjae Jeong","raw_affiliation_strings":["AI Center, NCSOFT,Speech Lab,Seongnam,Gyeonggi-do,Republic of Korea","Speech Lab, AI Center, NCSOFT, Seongnam, Gyeonggi-do, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"AI Center, NCSOFT,Speech Lab,Seongnam,Gyeonggi-do,Republic of Korea","institution_ids":["https://openalex.org/I4210135449"]},{"raw_affiliation_string":"Speech Lab, AI Center, NCSOFT, Seongnam, Gyeonggi-do, Republic of Korea","institution_ids":["https://openalex.org/I4210135449"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052468556","display_name":"Hoon Young Cho","orcid":"https://orcid.org/0000-0002-6850-6580"},"institutions":[{"id":"https://openalex.org/I4210135449","display_name":"NCSOFT (South Korea)","ror":"https://ror.org/03q4mza74","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210135449"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hoon-Young Cho","raw_affiliation_strings":["AI Center, NCSOFT,Speech Lab,Seongnam,Gyeonggi-do,Republic of Korea","Speech Lab, AI Center, NCSOFT, Seongnam, Gyeonggi-do, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"AI Center, NCSOFT,Speech Lab,Seongnam,Gyeonggi-do,Republic of Korea","institution_ids":["https://openalex.org/I4210135449"]},{"raw_affiliation_string":"Speech Lab, AI Center, NCSOFT, Seongnam, Gyeonggi-do, Republic of Korea","institution_ids":["https://openalex.org/I4210135449"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5018321415"],"corresponding_institution_ids":["https://openalex.org/I4210135449"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03556208,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8264","last_page":"8268"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9980999827384949,"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":0.9959999918937683,"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/utterance","display_name":"Utterance","score":0.8973020315170288},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7836392521858215},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.772997260093689},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6156013607978821},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5365362763404846},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4858819842338562},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47570309042930603},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4713278114795685},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.41353243589401245},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3742203712463379},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10099285840988159}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.8973020315170288},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7836392521858215},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.772997260093689},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6156013607978821},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5365362763404846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4858819842338562},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47570309042930603},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4713278114795685},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.41353243589401245},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3742203712463379},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10099285840988159},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053190","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053190","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1485103818","https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1606054028","https://openalex.org/W1815080316","https://openalex.org/W2028825255","https://openalex.org/W2034537249","https://openalex.org/W2086267546","https://openalex.org/W2135936685","https://openalex.org/W2143183271","https://openalex.org/W2145077480","https://openalex.org/W2394740500","https://openalex.org/W2594395650","https://openalex.org/W2626964143","https://openalex.org/W2913566369","https://openalex.org/W2972823380","https://openalex.org/W6631362777"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2333799855","https://openalex.org/W2351687372","https://openalex.org/W2004087835","https://openalex.org/W2314871050"],"abstract_inverted_index":{"The":[0,65,94],"purpose":[1],"of":[2,29,38,48,73,86],"this":[3],"study":[4],"is":[5],"to":[6,53,78],"detect":[7],"the":[8,27,35,44,70,84,99],"mismatch":[9,114],"between":[10,31,115],"text":[11],"script":[12],"and":[13,34,117],"voice-over.":[14],"For":[15],"this,":[16],"we":[17],"present":[18],"a":[19,32,39,79,87,104],"novel":[20],"utterance":[21,89],"verification":[22],"(UV)":[23],"method,":[24,67],"which":[25],"calculates":[26],"degree":[28],"correspondence":[30],"voice-over":[33,88],"phoneme":[36,45,75,80],"sequence":[37,81],"script.":[40,93],"We":[41],"found":[42],"that":[43,98],"recognition":[46,71],"probabilities":[47],"exaggerated":[49],"voice-overs":[50],"decrease":[51],"compared":[52],"ordinary":[54],"utterances,":[55],"but":[56],"their":[57],"rankings":[58],"do":[59],"not":[60],"demonstrate":[61],"any":[62],"significant":[63],"change.":[64],"proposed":[66,100],"therefore,":[68],"uses":[69],"ranking":[72],"each":[74],"segment":[76],"corresponding":[77,92],"for":[82,90,112],"measuring":[83],"confidence":[85],"its":[91],"experimental":[95],"results":[96],"show":[97],"UV":[101],"method":[102],"outperforms":[103],"state-of-the-art":[105],"approach":[106],"using":[107],"cross":[108],"modal":[109],"attention":[110],"used":[111],"detecting":[113],"speech":[116],"transcription.":[118]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}