{"id":"https://openalex.org/W4415433273","doi":"https://doi.org/10.21437/interspeech.2025-1443","title":"Synthesizing Speech with Selected Perceptual Voice Qualities \u2013 A Case Study with Creaky Voice","display_name":"Synthesizing Speech with Selected Perceptual Voice Qualities \u2013 A Case Study with Creaky Voice","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433273","doi":"https://doi.org/10.21437/interspeech.2025-1443"},"language":null,"primary_location":{"id":"doi:10.21437/interspeech.2025-1443","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1443","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":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2511.05143","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049869565","display_name":"Frederik Rautenberg","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Frederik Rautenberg","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022762565","display_name":"Fritz Seebauer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fritz Seebauer","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042219582","display_name":"Jana Wiechmann","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jana Wiechmann","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009710583","display_name":"Michael Kuhlmann","orcid":"https://orcid.org/0000-0003-3664-6922"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Kuhlmann","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070024202","display_name":"Petra Wagner","orcid":"https://orcid.org/0000-0001-6662-3612"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Petra Wagner","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5082075598","display_name":"Reinhold Haeb\u2010Umbach","orcid":"https://orcid.org/0000-0001-9468-7330"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Reinhold Haeb-Umbach","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5049869565"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1667968,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1633","last_page":"1637"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.8586999773979187,"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":0.8586999773979187,"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":0.8349999785423279,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.8015999794006348,"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/perception","display_name":"Perception","score":0.6687999963760376},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5285000205039978},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.505299985408783},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.43939998745918274},{"id":"https://openalex.org/keywords/speech-perception","display_name":"Speech perception","score":0.27639999985694885}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6881999969482422},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6687999963760376},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5873000025749207},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5285000205039978},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.505299985408783},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.43939998745918274},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3172000050544739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29420000314712524},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29339998960494995},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.27639999985694885},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.25600001215934753}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-1443","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1443","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:2511.05143","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.05143","pdf_url":"https://arxiv.org/pdf/2511.05143","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2511.05143","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.05143","pdf_url":"https://arxiv.org/pdf/2511.05143","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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":"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":{"The":[0],"control":[1],"of":[2,12,60,67,74],"perceptual":[3],"voice":[4],"qualities":[5],"in":[6],"a":[7,40,47,91],"text-to-speech":[8],"(TTS)":[9],"system":[10],"is":[11,44,58],"interest":[13],"for":[14],"applications":[15],"where":[16],"unmanipu-":[17],"lated":[18],"and":[19],"manipulated":[20],"speech":[21],"probes":[22],"can":[23],"serve":[24],"to":[25,34,98],"illustrate":[26],"pho-":[27],"netic":[28],"concepts":[29],"that":[30,39,43],"are":[31],"otherwise":[32],"difficult":[33],"grasp.":[35],"Here,":[36],"we":[37],"show":[38],"TTS":[41],"system,":[42],"augmented":[45],"with":[46],"global":[48],"speaker":[49],"attribute":[50],"manipulation":[51,89],"block":[52],"based":[53],"on":[54],"normalizing":[55],"flows1":[56],",":[57],"capable":[59],"correctly":[61],"manipulating":[62],"the":[63,72,99],"non-persistent,":[64],"localized":[65],"quality":[66],"creaky":[68],"voice,":[69],"thus":[70],"avoiding":[71],"necessity":[73],"a,":[75],"typi-":[76],"cally":[77],"unreliable,":[78],"frame-wise":[79],"creak":[80,88],"predictor.":[81],"Subjective":[82],"listen-":[83],"ing":[84],"tests":[85],"confirm":[86],"successful":[87],"at":[90],"slightly":[92],"re-":[93],"duced":[94],"MOS":[95],"score":[96],"compared":[97],"original":[100],"recording.":[101]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}
