{"id":"https://openalex.org/W2085065903","doi":"https://doi.org/10.1145/2662996.2663014","title":"Automatic Pronunciation Assistance on Video","display_name":"Automatic Pronunciation Assistance on Video","publication_year":2014,"publication_date":"2014-11-03","ids":{"openalex":"https://openalex.org/W2085065903","doi":"https://doi.org/10.1145/2662996.2663014","mag":"2085065903"},"language":"en","primary_location":{"id":"doi:10.1145/2662996.2663014","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2662996.2663014","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st International Workshop on Perception Inspired Video 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/A5013549596","display_name":"Mar\u00eda Pantoja","orcid":"https://orcid.org/0000-0002-1942-9769"},"institutions":[{"id":"https://openalex.org/I16269868","display_name":"Santa Clara University","ror":"https://ror.org/03ypqe447","country_code":"US","type":"education","lineage":["https://openalex.org/I16269868"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Maria Pantoja","raw_affiliation_strings":["Santa Clara University, Santa Clara, CA, USA","Santa Clara University, Santa Clara, CA - USA"],"affiliations":[{"raw_affiliation_string":"Santa Clara University, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I16269868"]},{"raw_affiliation_string":"Santa Clara University, Santa Clara, CA - USA","institution_ids":["https://openalex.org/I16269868"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5013549596"],"corresponding_institution_ids":["https://openalex.org/I16269868"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14611423,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"37","last_page":"38"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9947999715805054,"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":0.9947999715805054,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9905999898910522,"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":0.9713000059127808,"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/pronunciation","display_name":"Pronunciation","score":0.9544358253479004},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8816068768501282},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6168616414070129},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49689915776252747},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.46134665608406067},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46005624532699585},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4403040409088135},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10198187828063965}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.9544358253479004},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8816068768501282},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6168616414070129},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49689915776252747},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.46134665608406067},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46005624532699585},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4403040409088135},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10198187828063965},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2662996.2663014","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2662996.2663014","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st International Workshop on Perception Inspired Video Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8399999737739563}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W201042064","https://openalex.org/W2130639400","https://openalex.org/W2164598857","https://openalex.org/W2980286501"],"related_works":["https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W2041273198","https://openalex.org/W1599055764","https://openalex.org/W2131711534","https://openalex.org/W2149163000","https://openalex.org/W2962858469","https://openalex.org/W2289873871","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"In":[0],"this":[1],"article":[2],"we":[3],"present":[4],"a":[5,19,39,91,110],"novel":[6],"method":[7],"that":[8,98],"uses":[9],"image":[10,51],"and":[11,23,50,57,73],"speech":[12,49],"processing":[13],"techniques":[14,44],"to":[15,65,78,81,88,94,106],"analyze":[16],"video":[17],"from":[18,38],"second":[20,112],"language":[21,113],"learner":[22],"provides":[24],"speaker's":[25],"pronunciation":[26,29,103],"training.":[27],"The":[28,45,70],"recommendation":[30],"provided":[31,108],"for":[32,90],"the":[33,59,67,74,86],"speaker":[34],"will":[35],"be":[36],"selected":[37],"database":[40],"using":[41],"machine":[42],"learning":[43],"model":[46],"presented":[47],"integrates":[48],"recognition":[52],"technology":[53],"capable":[54],"of":[55],"quantizing":[56],"analyzing":[58],"learner's":[60],"input":[61],"providing":[62],"feed-back":[63],"data":[64],"evaluate":[66],"model's":[68],"performance.":[69],"image/audio":[71],"analysis":[72],"expert":[75],"system":[76],"needed":[77],"provide":[79],"recommendations":[80,104],"students":[82],"are":[83],"implemented":[84],"on":[85],"GPU":[87],"allow":[89],"fast":[92],"feedback":[93],"students.":[95],"Results":[96],"show":[97],"our":[99],"methodology":[100],"accurately":[101],"assigns":[102],"equivalent":[105],"those":[107],"by":[109],"human":[111],"(L2)":[114],"instructor.":[115]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}