{"id":"https://openalex.org/W4416771742","doi":"https://doi.org/10.1109/sped67700.2025.11251681","title":"Style-Controlled VALL-E for Few-Shot Emotional German TTS","display_name":"Style-Controlled VALL-E for Few-Shot Emotional German TTS","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416771742","doi":"https://doi.org/10.1109/sped67700.2025.11251681"},"language":null,"primary_location":{"id":"doi:10.1109/sped67700.2025.11251681","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped67700.2025.11251681","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.1109/SpeD67700.2025.11251681","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Rami Kammoun","orcid":null},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"Rami Kammoun","raw_affiliation_strings":["Budapest University of Technology and Economics,Department of Telecommunications and Artificial Intelligence,Budapest,Hungary"],"affiliations":[{"raw_affiliation_string":"Budapest University of Technology and Economics,Department of Telecommunications and Artificial Intelligence,Budapest,Hungary","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086670617","display_name":"Mohammed Salah Al-Radhi","orcid":"https://orcid.org/0000-0003-3094-6916"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Mohammed Salah Al-Radhi","raw_affiliation_strings":["Budapest University of Technology and Economics,Department of Telecommunications and Artificial Intelligence,Budapest,Hungary"],"affiliations":[{"raw_affiliation_string":"Budapest University of Technology and Economics,Department of Telecommunications and Artificial Intelligence,Budapest,Hungary","institution_ids":["https://openalex.org/I29770179"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I29770179"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37860725,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"75","last_page":"80"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.2757999897003174,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.2757999897003174,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.23960000276565552,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.08269999921321869,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.8629000186920166},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.4740000069141388},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.4212999939918518},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.32359999418258667},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3160000145435333}],"concepts":[{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.8629000186920166},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.5823000073432922},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.48840001225471497},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.4740000069141388},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45989999175071716},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4528000056743622},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.4212999939918518},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3725000023841858},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32839998602867126},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3160000145435333},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.3019999861717224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2856999933719635},{"id":"https://openalex.org/C2780733359","wikidata":"https://www.wikidata.org/wiki/Q331769","display_name":"Mood","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/sped67700.2025.11251681","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped67700.2025.11251681","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","raw_type":"proceedings-article"},{"id":"pmh:oai:zenodo.org:17771914","is_oa":true,"landing_page_url":"https://doi.org/10.1109/SpeD67700.2025.11251681","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SpeD, International Conference on Speech Technology and Human-Computer Dialogue, Cluj-Napoca, Romania, 19-22 October 2025","raw_type":"info:eu-repo/semantics/conferenceProceedings"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:17771914","is_oa":true,"landing_page_url":"https://doi.org/10.1109/SpeD67700.2025.11251681","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SpeD, International Conference on Speech Technology and Human-Computer Dialogue, Cluj-Napoca, Romania, 19-22 October 2025","raw_type":"info:eu-repo/semantics/conferenceProceedings"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2758788159","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W3197858274","https://openalex.org/W3198791321","https://openalex.org/W4226421465","https://openalex.org/W4296068758","https://openalex.org/W4375869117","https://openalex.org/W4391745456","https://openalex.org/W4403653255","https://openalex.org/W4406417959","https://openalex.org/W4408354728"],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"an":[2],"expressive":[3,58],"German":[4,35,75],"Text-to-Speech":[5],"(TTS)":[6],"system":[7],"built":[8],"on":[9],"a":[10,20],"modified":[11],"VALL-E":[12],"neural":[13],"codec":[14],"language":[15],"model.":[16],"Our":[17,48],"approach":[18],"introduces":[19],"style-conditioning":[21],"mechanism":[22],"to":[23,56],"enable":[24],"emotional":[25,82],"and":[26,41,53,73],"prosodic":[27],"control":[28],"during":[29],"speech":[30],"synthesis.":[31],"Using":[32],"the":[33],"Thorsten":[34],"Emotional":[36],"TTS":[37,83],"dataset,":[38],"we":[39],"preprocess":[40],"augment":[42],"2,400":[43],"utterances":[44],"across":[45],"8":[46],"emotions.":[47],"model":[49],"integrates":[50],"emotion":[51],"tokens":[52],"style":[54],"embeddings":[55],"guide":[57],"generation":[59],"without":[60],"explicit":[61],"supervision.":[62],"Preliminary":[63],"results":[64],"suggest":[65],"that":[66],"this":[67],"method":[68],"can":[69],"produce":[70],"prosodically":[71],"varied":[72],"natural-sounding":[74],"speech,":[76],"demonstrating":[77],"its":[78],"potential":[79],"in":[80],"low-resource":[81],"settings.":[84]},"counts_by_year":[],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-11-27T00:00:00"}