{"id":"https://openalex.org/W4385732548","doi":"https://doi.org/10.1145/3594806.3596536","title":"Practical Study of Deep Learning Models for Speech Synthesis","display_name":"Practical Study of Deep Learning Models for Speech Synthesis","publication_year":2023,"publication_date":"2023-07-05","ids":{"openalex":"https://openalex.org/W4385732548","doi":"https://doi.org/10.1145/3594806.3596536"},"language":"en","primary_location":{"id":"doi:10.1145/3594806.3596536","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3594806.3596536","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th International Conference on PErvasive Technologies Related to Assistive Environments","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/2078.1/277255","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057250210","display_name":"Quentin Langlois","orcid":"https://orcid.org/0009-0006-7135-3809"},"institutions":[{"id":"https://openalex.org/I95674353","display_name":"UCLouvain","ror":"https://ror.org/02495e989","country_code":"BE","type":"education","lineage":["https://openalex.org/I95674353"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Quentin Langlois","raw_affiliation_strings":["UCLouvain, Belgium"],"raw_orcid":"https://orcid.org/0009-0006-7135-3809","affiliations":[{"raw_affiliation_string":"UCLouvain, Belgium","institution_ids":["https://openalex.org/I95674353"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020592313","display_name":"S\u00e9bastien Jodogne","orcid":"https://orcid.org/0000-0001-6685-7398"},"institutions":[{"id":"https://openalex.org/I95674353","display_name":"UCLouvain","ror":"https://ror.org/02495e989","country_code":"BE","type":"education","lineage":["https://openalex.org/I95674353"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"S\u00e9bastien Jodogne","raw_affiliation_strings":["UCLouvain, Belgium"],"raw_orcid":"https://orcid.org/0000-0001-6685-7398","affiliations":[{"raw_affiliation_string":"UCLouvain, Belgium","institution_ids":["https://openalex.org/I95674353"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I95674353"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"700","last_page":"706"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9984999895095825,"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":0.9980000257492065,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8409242630004883},{"id":"https://openalex.org/keywords/usable","display_name":"USable","score":0.8311253786087036},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.7527554035186768},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.7219678163528442},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.6766764521598816},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6625258922576904},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5596379041671753},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5373531579971313},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49525657296180725},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4493730664253235},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4146324098110199},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.380845308303833},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.34152650833129883}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8409242630004883},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.8311253786087036},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.7527554035186768},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7219678163528442},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.6766764521598816},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6625258922576904},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5596379041671753},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5373531579971313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49525657296180725},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4493730664253235},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4146324098110199},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.380845308303833},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.34152650833129883},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3594806.3596536","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3594806.3596536","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th International Conference on PErvasive Technologies Related to Assistive Environments","raw_type":"proceedings-article"},{"id":"pmh:oai:dial.uclouvain.be:boreal:277255","is_oa":true,"landing_page_url":"http://hdl.handle.net/2078.1/277255","pdf_url":null,"source":{"id":"https://openalex.org/S4306400166","display_name":"Digital Access to Libraries","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800384882","host_organization_name":"Harris County Public Library","host_organization_lineage":["https://openalex.org/I2800384882"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:dial.uclouvain.be:boreal:277255","is_oa":true,"landing_page_url":"http://hdl.handle.net/2078.1/277255","pdf_url":null,"source":{"id":"https://openalex.org/S4306400166","display_name":"Digital Access to Libraries","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800384882","host_organization_name":"Harris County Public Library","host_organization_lineage":["https://openalex.org/I2800384882"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8299999833106995,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2766049740","https://openalex.org/W3211329195","https://openalex.org/W4313679638","https://openalex.org/W6600650897","https://openalex.org/W6604730619"],"related_works":["https://openalex.org/W4206357785","https://openalex.org/W4281381188","https://openalex.org/W3192840557","https://openalex.org/W2951211570","https://openalex.org/W4375928479","https://openalex.org/W3167935049","https://openalex.org/W3023427754","https://openalex.org/W3131673289","https://openalex.org/W4393011546","https://openalex.org/W3198847674"],"abstract_inverted_index":{"Speech":[0],"synthesis":[1],"systems,":[2,8],"also":[3,86],"known":[4],"as":[5,17],"Text-To-Speech":[6],"(TTS)":[7],"are":[9,68,131],"increasingly":[10],"frequent":[11],"nowadays,":[12],"with":[13,133,164,176],"multiple":[14],"applications":[15,30],"such":[16,84],"voice":[18],"assistants":[19],"and":[20,117],"screen":[21],"readers":[22],"for":[23,72,99,140],"visually":[24],"impaired":[25],"or":[26],"blind":[27],"people.":[28],"These":[29],"require":[31],"strong":[32],"real-time":[33],"capabilities":[34],"to":[35,124,135],"be":[36,42,154],"usable":[37],"in":[38,50,62,80,112],"practice,":[39],"which":[40,57,95],"can":[41,153],"at":[43],"the":[44,51,63,105,141],"cost":[45],"of":[46,65,76,91,107,114,119,168],"a":[47,88,158,161,165],"reduced":[48],"quality":[49,93,127,150,170],"synthesized":[52],"voices.":[53],"Deep":[54],"Learning":[55],"models,":[56],"have":[58],"shown":[59],"impressive":[60],"results":[61],"task":[64],"audio":[66],"generation,":[67],"hardly":[69],"ever":[70],"used":[71],"everyday":[73],"TTS":[74,137],"because":[75],"their":[77],"high":[78],"demand":[79],"computational":[81],"resources.":[82],"Training":[83],"models":[85,152],"requires":[87],"large":[89],"amount":[90,118],"good":[92,126,149,169],"data,":[94,171],"is":[96,122,147],"not":[97],"available":[98,139],"most":[100],"languages.":[101],"This":[102],"paper":[103],"explores":[104],"benefits":[106],"cross-lingual":[108],"transfer":[109,174],"learning,":[110],"both":[111],"terms":[113],"training":[115],"time":[116],"data":[120],"that":[121,148],"needed":[123],"obtain":[125],"models.":[128],"Our":[129],"contributions":[130],"evaluated":[132],"respect":[134],"other":[136],"systems":[138],"French":[142],"language.":[143],"The":[144],"main":[145],"observation":[146],"single-speaker":[151],"trained":[155],"within":[156],"half":[157],"week":[159],"on":[160],"single":[162],"GPU,":[163],"limited":[166],"number":[167],"by":[172],"combining":[173],"learning":[175],"few-shot":[177],"learning.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}