{"id":"https://openalex.org/W4415433306","doi":"https://doi.org/10.21437/interspeech.2025-1192","title":"Voice Impression Control in Zero-Shot TTS","display_name":"Voice Impression Control in Zero-Shot TTS","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433306","doi":"https://doi.org/10.21437/interspeech.2025-1192"},"language":null,"primary_location":{"id":"doi:10.21437/interspeech.2025-1192","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1192","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.05688","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019102133","display_name":"Ken\u2010ichi Fujita","orcid":"https://orcid.org/0000-0002-8362-2694"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kenichi Fujita","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Shota Horiguchi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shota Horiguchi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5068604686","display_name":"Yusuke Ijima","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yusuke Ijima","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4363","last_page":"4367"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.722599983215332,"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":0.722599983215332,"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/impression","display_name":"Impression","score":0.8086000084877014},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5831000208854675},{"id":"https://openalex.org/keywords/phonation","display_name":"Phonation","score":0.3889000117778778},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3806000053882599},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.37599998712539673},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.3212999999523163},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.3149999976158142}],"concepts":[{"id":"https://openalex.org/C2776684213","wikidata":"https://www.wikidata.org/wiki/Q6007582","display_name":"Impression","level":2,"score":0.8086000084877014},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6220999956130981},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5831000208854675},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5473999977111816},{"id":"https://openalex.org/C173988693","wikidata":"https://www.wikidata.org/wiki/Q678132","display_name":"Phonation","level":2,"score":0.3889000117778778},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3871999979019165},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3806000053882599},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.37599998712539673},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34130001068115234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32170000672340393},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.3212999999523163},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3149999976158142},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.2994000017642975},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C110346835","wikidata":"https://www.wikidata.org/wiki/Q665141","display_name":"Precedent","level":3,"score":0.28369998931884766},{"id":"https://openalex.org/C137584468","wikidata":"https://www.wikidata.org/wiki/Q35395","display_name":"Phonetics","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C2781032008","wikidata":"https://www.wikidata.org/wiki/Q424083","display_name":"Acoustic phonetics","level":3,"score":0.2651999890804291},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2025-1192","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1192","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.05688","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.05688","pdf_url":"https://arxiv.org/pdf/2506.05688","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:doi:10.48550/arxiv.2506.05688","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.05688","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.05688","pdf_url":"https://arxiv.org/pdf/2506.05688","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Para-/non-linguistic":[0],"information":[1,23],"in":[2,6,42,74],"speech":[3],"is":[4],"pivotal":[5],"shaping":[7],"the":[8,52,95,100],"listeners'":[9],"impression.":[10],"Although":[11],"zero-shot":[12,43],"text-to-speech":[13],"(TTS)":[14],"has":[15],"achieved":[16],"high":[17],"speaker":[18],"fidelity,":[19],"modulating":[20],"subtle":[21],"para-/non-linguistic":[22],"to":[24,50],"control":[25,40],"perceived":[26],"voice":[27,38,56],"characteristics,":[28],"i.e.,":[29],"impressions,":[30],"remains":[31],"challenging.":[32],"We":[33],"have":[34,69],"therefore":[35],"developed":[36],"a":[37,47,82,90],"impression":[39,57,75],"method":[41],"TTS":[44],"that":[45],"utilizes":[46],"low-dimensional":[48],"vector":[49,80],"represent":[51],"intensities":[53],"of":[54,63,94],"various":[55],"pairs":[58],"(e.g.,":[59],"dark-bright).":[60],"The":[61],"results":[62],"both":[64],"objective":[65],"and":[66],"subjective":[67],"evaluations":[68],"demonstrated":[70],"our":[71,110],"method's":[72],"effectiveness":[73],"control.":[76],"Furthermore,":[77],"generating":[78],"this":[79],"via":[81],"large":[83],"language":[84,92],"model":[85],"enables":[86],"target-impression":[87],"generation":[88],"from":[89],"natural":[91],"description":[93],"desired":[96],"impression,":[97],"thus":[98],"eliminating":[99],"need":[101],"for":[102],"manual":[103],"optimization.":[104],"Audio":[105],"examples":[106],"are":[107],"available":[108],"on":[109],"demo":[111],"page":[112],"(https://ntt-hilab-gensp.github.io/is2025voiceimpression/).":[113]},"counts_by_year":[],"updated_date":"2026-07-27T08:26:11.824852","created_date":"2025-10-24T00:00:00"}