{"id":"https://openalex.org/W3213879636","doi":"https://doi.org/10.1145/3426020.3426168","title":"Korean Voice Annotation Program","display_name":"Korean Voice Annotation Program","publication_year":2020,"publication_date":"2020-09-17","ids":{"openalex":"https://openalex.org/W3213879636","doi":"https://doi.org/10.1145/3426020.3426168","mag":"3213879636"},"language":"en","primary_location":{"id":"doi:10.1145/3426020.3426168","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3426020.3426168","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 9th International Conference on Smart Media and Applications","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/A5102431374","display_name":"Sin Woo Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I152238500","display_name":"Chosun University","ror":"https://ror.org/01zt9a375","country_code":"KR","type":"education","lineage":["https://openalex.org/I152238500"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Sin Woo Lee","raw_affiliation_strings":["Chosun University, S. Korea"],"affiliations":[{"raw_affiliation_string":"Chosun University, S. Korea","institution_ids":["https://openalex.org/I152238500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110677934","display_name":"Jong Ho Paik","orcid":null},"institutions":[{"id":"https://openalex.org/I98600543","display_name":"Seoul Women's University","ror":"https://ror.org/04b2fhx54","country_code":"KR","type":"education","lineage":["https://openalex.org/I98600543"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jong Ho Paik","raw_affiliation_strings":["Seoul Women University, S. Korea"],"affiliations":[{"raw_affiliation_string":"Seoul Women University, S. Korea","institution_ids":["https://openalex.org/I98600543"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016894750","display_name":"In Seop Na","orcid":"https://orcid.org/0000-0001-6471-043X"},"institutions":[{"id":"https://openalex.org/I152238500","display_name":"Chosun University","ror":"https://ror.org/01zt9a375","country_code":"KR","type":"education","lineage":["https://openalex.org/I152238500"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"In Seop Na","raw_affiliation_strings":["Chosun University, S. Korea"],"affiliations":[{"raw_affiliation_string":"Chosun University, S. Korea","institution_ids":["https://openalex.org/I152238500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102431374"],"corresponding_institution_ids":["https://openalex.org/I152238500"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22502857,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"460","last_page":"463"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9891999959945679,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9891999959945679,"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"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9599999785423279,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9575999975204468,"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/closed-captioning","display_name":"Closed captioning","score":0.9775813817977905},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8011334538459778},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.688586413860321},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6217436790466309},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.613416314125061},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5736749172210693},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5547614097595215},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5491266250610352},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5327154994010925},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5020451545715332},{"id":"https://openalex.org/keywords/automatic-image-annotation","display_name":"Automatic image annotation","score":0.4701557159423828},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.468166321516037},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4649471342563629},{"id":"https://openalex.org/keywords/language-translation","display_name":"Language translation","score":0.42703524231910706},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3617709279060364},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.24342599511146545}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9775813817977905},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8011334538459778},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.688586413860321},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6217436790466309},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.613416314125061},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5736749172210693},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5547614097595215},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5491266250610352},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5327154994010925},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5020451545715332},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.4701557159423828},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.468166321516037},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4649471342563629},{"id":"https://openalex.org/C2986862884","wikidata":"https://www.wikidata.org/wiki/Q7553","display_name":"Language translation","level":3,"score":0.42703524231910706},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3617709279060364},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.24342599511146545}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3426020.3426168","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3426020.3426168","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 9th International Conference on Smart Media and Applications","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":6,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2123215356","https://openalex.org/W2145262511","https://openalex.org/W2888469204","https://openalex.org/W2963881378","https://openalex.org/W2964243274"],"related_works":["https://openalex.org/W2000013842","https://openalex.org/W4362495644","https://openalex.org/W2134714056","https://openalex.org/W4321065355","https://openalex.org/W2997015083","https://openalex.org/W3127743011","https://openalex.org/W3213879636","https://openalex.org/W2892009878","https://openalex.org/W3167690611","https://openalex.org/W4379381477"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3],"way":[4],"to":[5,8],"convert":[6],"image":[7,50],"voice":[9,55],"using":[10],"Image":[11,13,24,28,31],"Segmentation,":[12],"Captioning":[14,25,32],"and":[15,30,34,51],"Speech":[16,36,40],"Synthesis":[17,37,41],"techniques.":[18],"At":[19],"first,":[20],"we":[21,64],"designed":[22],"the":[23,35,49,54,61,89,94],"Unit(ICU)":[26],"with":[27,39],"Segmentation":[29],"model,":[33],"Unit(SSU)":[38],"model.":[42],"Secondly,":[43],"ICU":[44],"outputs":[45],"predicted":[46,57],"sentence":[47],"from":[48,56],"SSU":[52],"generated":[53],"sentence.":[58],"To":[59],"evaluate":[60],"proposed":[62],"method,":[63],"used":[65,73,87],"sentence_blue":[66],"score":[67],"of":[68,77],"NLTK":[69],"which":[70],"is":[71],"widely":[72],"as":[74],"an":[75],"indicator":[76],"machine":[78],"translation.":[79],"We":[80],"hope":[81],"that":[82],"our":[83],"algorithms":[84],"may":[85],"be":[86],"for":[88],"visual":[90],"impaired":[91],"people":[92],"in":[93],"future.":[95]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}