{"id":"https://openalex.org/W4408352885","doi":"https://doi.org/10.1109/icassp49660.2025.10889011","title":"Maintaining Prosodic Consistency in Automatic Dubbing for Better Isochrony","display_name":"Maintaining Prosodic Consistency in Automatic Dubbing for Better Isochrony","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352885","doi":"https://doi.org/10.1109/icassp49660.2025.10889011"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5107931366","display_name":"Parnia Bahar","orcid":null},"institutions":[{"id":"https://openalex.org/I99977706","display_name":"FH Aachen","ror":"https://ror.org/04tqgg260","country_code":"DE","type":"education","lineage":["https://openalex.org/I99977706"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Parnia Bahar","raw_affiliation_strings":["AppTek,Aachen,Germany"],"affiliations":[{"raw_affiliation_string":"AppTek,Aachen,Germany","institution_ids":["https://openalex.org/I99977706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091092804","display_name":"Alejandro P\u00e9rez-Gonz\u00e1lez-de-Martos","orcid":"https://orcid.org/0000-0002-0453-2114"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alejandro P\u00e9rez","raw_affiliation_strings":["AppTek,Valencia,Spain"],"affiliations":[{"raw_affiliation_string":"AppTek,Valencia,Spain","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053563948","display_name":"Javier Iranzo-S\u00e1nchez","orcid":"https://orcid.org/0000-0002-4035-3295"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Javier Iranzo-S\u00e1nchez","raw_affiliation_strings":["AppTek,Valencia,Spain"],"affiliations":[{"raw_affiliation_string":"AppTek,Valencia,Spain","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5107931366"],"corresponding_institution_ids":["https://openalex.org/I99977706"],"apc_list":null,"apc_paid":null,"fwci":2.8414,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89780073,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9782000184059143,"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":0.9782000184059143,"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/T10860","display_name":"Speech and Audio Processing","score":0.9467999935150146,"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/T12031","display_name":"Speech and dialogue systems","score":0.9243000149726868,"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/consistency","display_name":"Consistency (knowledge bases)","score":0.5979710817337036},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5977899432182312},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41139650344848633},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34353721141815186},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24705612659454346}],"concepts":[{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5979710817337036},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5977899432182312},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41139650344848633},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34353721141815186},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24705612659454346}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311649","display_name":"Ministry of Education","ror":"https://ror.org/036nq5137"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2747874407","https://openalex.org/W2963250244","https://openalex.org/W2963532001","https://openalex.org/W2963925437","https://openalex.org/W2971345947","https://openalex.org/W2972425358","https://openalex.org/W3037838322","https://openalex.org/W3084396630","https://openalex.org/W3158927431","https://openalex.org/W3161049737","https://openalex.org/W4225302758","https://openalex.org/W4296070449","https://openalex.org/W4382202818","https://openalex.org/W4385245566","https://openalex.org/W4385570170","https://openalex.org/W4385822664","https://openalex.org/W6631190155","https://openalex.org/W6679436768","https://openalex.org/W6780680273","https://openalex.org/W6850505448"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"One":[0],"of":[1,5,11,37,73,109,115],"the":[2,19,30,34,38,60,65,70,77,82,89,107,110],"major":[3],"requirements":[4],"automatic":[6],"dubbing,":[7],"as":[8],"an":[9],"extension":[10],"speech-to-speech":[12],"translation,":[13],"is":[14],"isochrony.":[15],"It":[16],"refers":[17],"to":[18,68,92],"fact":[20],"that":[21],"dubbed":[22],"speech":[23,62],"should":[24],"line":[25],"up":[26],"in":[27,76,113],"time":[28],"with":[29],"original":[31,61],"speech,":[32],"matching":[33],"phrase-pause":[35,63],"arrangement":[36],"source":[39],"utterance.":[40],"To":[41],"achieve":[42],"this,":[43],"we":[44],"explore":[45],"and":[46,55,119],"compare":[47],"two":[48,102],"alternative":[49],"prosodic":[50,86],"alignment":[51,87],"modeling":[52],"techniques:":[53],"Prosodic-only":[54],"joint":[56],"Prosodic-MT.":[57],"Based":[58],"on":[59,101],"structure,":[64],"former":[66],"aims":[67],"predict":[69],"optimal":[71],"position":[72],"pause":[74],"markers":[75],"target":[78],"text":[79],"sequence,":[80],"while":[81],"latter":[83],"implicitly":[84],"incorporates":[85],"within":[88],"translation":[90,96,117],"process":[91],"generate":[93],"a":[94],"suitable":[95],"for":[97],"dubbing.":[98],"Empirical":[99],"results":[100],"publicly":[103],"available":[104],"datasets":[105],"demonstrate":[106],"effectiveness":[108],"proposed":[111],"approaches":[112],"terms":[114],"both":[116],"quality":[118],"syllables-based":[120],"isochrony":[121],"metrics.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}