{"id":"https://openalex.org/W4393656336","doi":"https://doi.org/10.1109/o-cocosda60357.2023.10482965","title":"Generating Speech with Prosodic Prominence based on SSL-Visually Grounded Models","display_name":"Generating Speech with Prosodic Prominence based on SSL-Visually Grounded Models","publication_year":2023,"publication_date":"2023-12-04","ids":{"openalex":"https://openalex.org/W4393656336","doi":"https://doi.org/10.1109/o-cocosda60357.2023.10482965"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda60357.2023.10482965","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/o-cocosda60357.2023.10482965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 26th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","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/A5006828939","display_name":"Bella Septina Ika Hartanti","orcid":"https://orcid.org/0000-0003-1057-9389"},"institutions":[{"id":"https://openalex.org/I29617571","display_name":"University of Indonesia","ror":"https://ror.org/0116zj450","country_code":"ID","type":"education","lineage":["https://openalex.org/I29617571"]}],"countries":["ID"],"is_corresponding":true,"raw_author_name":"Bella Septina Ika Hartanti","raw_affiliation_strings":["University of Indonesia,Depok,Indonesia","University of Indonesia, Depok, Indonesia"],"affiliations":[{"raw_affiliation_string":"University of Indonesia,Depok,Indonesia","institution_ids":["https://openalex.org/I29617571"]},{"raw_affiliation_string":"University of Indonesia, Depok, Indonesia","institution_ids":["https://openalex.org/I29617571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066930701","display_name":"Dipta Tanaya","orcid":"https://orcid.org/0009-0000-1480-8041"},"institutions":[{"id":"https://openalex.org/I29617571","display_name":"University of Indonesia","ror":"https://ror.org/0116zj450","country_code":"ID","type":"education","lineage":["https://openalex.org/I29617571"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Dipta Tanaya","raw_affiliation_strings":["University of Indonesia,Depok,Indonesia","University of Indonesia, Depok, Indonesia"],"affiliations":[{"raw_affiliation_string":"University of Indonesia,Depok,Indonesia","institution_ids":["https://openalex.org/I29617571"]},{"raw_affiliation_string":"University of Indonesia, Depok, Indonesia","institution_ids":["https://openalex.org/I29617571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066073372","display_name":"Kurniawati Azizah","orcid":"https://orcid.org/0000-0002-3217-7025"},"institutions":[{"id":"https://openalex.org/I29617571","display_name":"University of Indonesia","ror":"https://ror.org/0116zj450","country_code":"ID","type":"education","lineage":["https://openalex.org/I29617571"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Kurniawati Azizah","raw_affiliation_strings":["University of Indonesia,Depok,Indonesia","University of Indonesia, Depok, Indonesia"],"affiliations":[{"raw_affiliation_string":"University of Indonesia,Depok,Indonesia","institution_ids":["https://openalex.org/I29617571"]},{"raw_affiliation_string":"University of Indonesia, Depok, Indonesia","institution_ids":["https://openalex.org/I29617571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109119353","display_name":"Dessi Puji Lestari","orcid":null},"institutions":[{"id":"https://openalex.org/I134635517","display_name":"Bandung Institute of Technology","ror":"https://ror.org/00apj8t60","country_code":"ID","type":"education","lineage":["https://openalex.org/I134635517"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Dessi Puji Lestari","raw_affiliation_strings":["Bandung Institute of Technology,Bandung,Indonesia","Bandung Institute of Technology, Bandung, Indonesia"],"affiliations":[{"raw_affiliation_string":"Bandung Institute of Technology,Bandung,Indonesia","institution_ids":["https://openalex.org/I134635517"]},{"raw_affiliation_string":"Bandung Institute of Technology, Bandung, Indonesia","institution_ids":["https://openalex.org/I134635517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021128017","display_name":"Ayu Purwarianti","orcid":"https://orcid.org/0000-0002-5016-3700"},"institutions":[{"id":"https://openalex.org/I134635517","display_name":"Bandung Institute of Technology","ror":"https://ror.org/00apj8t60","country_code":"ID","type":"education","lineage":["https://openalex.org/I134635517"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Ayu Purwarianti","raw_affiliation_strings":["Bandung Institute of Technology,Bandung,Indonesia","Bandung Institute of Technology, Bandung, Indonesia"],"affiliations":[{"raw_affiliation_string":"Bandung Institute of Technology,Bandung,Indonesia","institution_ids":["https://openalex.org/I134635517"]},{"raw_affiliation_string":"Bandung Institute of Technology, Bandung, Indonesia","institution_ids":["https://openalex.org/I134635517"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology,Ishikawa,Japan","Japan Advanced Institute of Science and Technology, Ishikawa, Japan"],"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology,Ishikawa,Japan","institution_ids":["https://openalex.org/I177738480"]},{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5006828939"],"corresponding_institution_ids":["https://openalex.org/I29617571"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21680747,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9812999963760376,"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/T12031","display_name":"Speech and dialogue systems","score":0.9812999963760376,"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/computer-science","display_name":"Computer science","score":0.6570501327514648},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.534274160861969},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43403276801109314},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.35555046796798706}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6570501327514648},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.534274160861969},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43403276801109314},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.35555046796798706},{"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:10.1109/o-cocosda60357.2023.10482965","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/o-cocosda60357.2023.10482965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 26th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","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":38,"referenced_works":["https://openalex.org/W1600722501","https://openalex.org/W2085013480","https://openalex.org/W2097998164","https://openalex.org/W2106447003","https://openalex.org/W2770743791","https://openalex.org/W2794490148","https://openalex.org/W2903739847","https://openalex.org/W2940544976","https://openalex.org/W2962862718","https://openalex.org/W2972699445","https://openalex.org/W2973026522","https://openalex.org/W2988907666","https://openalex.org/W3095545636","https://openalex.org/W3125687907","https://openalex.org/W3144667183","https://openalex.org/W3157555801","https://openalex.org/W3159481202","https://openalex.org/W3196475561","https://openalex.org/W3197216873","https://openalex.org/W3198123658","https://openalex.org/W3209059054","https://openalex.org/W3214634826","https://openalex.org/W4224875474","https://openalex.org/W4225300652","https://openalex.org/W4226474318","https://openalex.org/W4281736089","https://openalex.org/W4295731579","https://openalex.org/W4313023760","https://openalex.org/W4372337821","https://openalex.org/W4395957972","https://openalex.org/W6677994088","https://openalex.org/W6746238782","https://openalex.org/W6749555683","https://openalex.org/W6750489868","https://openalex.org/W6777694618","https://openalex.org/W6778823374","https://openalex.org/W6795261426","https://openalex.org/W6838843145"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"Despite":[0],"many":[1],"existing":[2],"works":[3],"that":[4,57,107],"address":[5],"expressive":[6],"speech":[7,18,29,91,127],"synthesis":[8],"with":[9,19,34,74,92],"a":[10,35,39,83,105],"desired":[11],"prosody,":[12],"few":[13],"have":[14],"focused":[15],"on":[16,53,82,96],"generating":[17],"prosody":[20,51,93],"prominence.":[21],"Most":[22],"previous":[23],"studies":[24],"addressing":[25],"this":[26,44],"issue":[27],"generate":[28],"from":[30],"given":[31],"text":[32,119],"labels":[33],"contrastive":[36,55,98],"focus":[37,56,99],"emphasizing":[38],"specific":[40],"word.":[41],"In":[42],"contrast,":[43],"paper":[45],"investigates":[46],"whether":[47],"we":[48],"can":[49,114],"control":[50],"based":[52,81,95],"the":[54,97,110,116],"appears":[58],"in":[59,78,104,129],"images.":[60,111],"Given":[61],"an":[62],"image":[63],"and":[64],"its":[65],"caption,":[66],"our":[67],"system":[68],"first":[69],"discovers":[70],"spoken":[71,102],"terms":[72,103],"associated":[73],"objects":[75],"or":[76],"situations":[77],"natural":[79],"images":[80],"self-supervised":[84],"visually":[85],"grounded":[86],"model.":[87],"Then":[88],"it":[89,122],"generates":[90],"prominence":[94],"of":[100],"these":[101],"way":[106],"best":[108],"describes":[109],"The":[112],"framework":[113],"perform":[115],"task":[117],"with/without":[118],"annotation,":[120],"making":[121],"applicable":[123],"for":[124],"untranscribed,":[125],"unsegmented":[126],"utterances":[128],"unknown":[130],"languages.":[131]},"counts_by_year":[],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}