{"id":"https://openalex.org/W4408353111","doi":"https://doi.org/10.1109/icassp49660.2025.10888012","title":"Speech Synthesis along Perceptual Voice Quality Dimensions","display_name":"Speech Synthesis along Perceptual Voice Quality Dimensions","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353111","doi":"https://doi.org/10.1109/icassp49660.2025.10888012"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888012","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888012","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/A5049869565","display_name":"Frederik Rautenberg","orcid":null},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Frederik Rautenberg","raw_affiliation_strings":["Paderborn University,Paderborn,Germany"],"affiliations":[{"raw_affiliation_string":"Paderborn University,Paderborn,Germany","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009710583","display_name":"Michael Kuhlmann","orcid":"https://orcid.org/0000-0003-3664-6922"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael Kuhlmann","raw_affiliation_strings":["Paderborn University,Paderborn,Germany"],"affiliations":[{"raw_affiliation_string":"Paderborn University,Paderborn,Germany","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022762565","display_name":"Fritz Seebauer","orcid":null},"institutions":[{"id":"https://openalex.org/I20121455","display_name":"Bielefeld University","ror":"https://ror.org/02hpadn98","country_code":"DE","type":"education","lineage":["https://openalex.org/I20121455"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Fritz Seebauer","raw_affiliation_strings":["Bielefeld University,Bielefeld,Germany"],"affiliations":[{"raw_affiliation_string":"Bielefeld University,Bielefeld,Germany","institution_ids":["https://openalex.org/I20121455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042219582","display_name":"Jana Wiechmann","orcid":null},"institutions":[{"id":"https://openalex.org/I20121455","display_name":"Bielefeld University","ror":"https://ror.org/02hpadn98","country_code":"DE","type":"education","lineage":["https://openalex.org/I20121455"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jana Wiechmann","raw_affiliation_strings":["Bielefeld University,Bielefeld,Germany"],"affiliations":[{"raw_affiliation_string":"Bielefeld University,Bielefeld,Germany","institution_ids":["https://openalex.org/I20121455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070024202","display_name":"Petra Wagner","orcid":"https://orcid.org/0000-0001-6662-3612"},"institutions":[{"id":"https://openalex.org/I20121455","display_name":"Bielefeld University","ror":"https://ror.org/02hpadn98","country_code":"DE","type":"education","lineage":["https://openalex.org/I20121455"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Petra Wagner","raw_affiliation_strings":["Bielefeld University,Bielefeld,Germany"],"affiliations":[{"raw_affiliation_string":"Bielefeld University,Bielefeld,Germany","institution_ids":["https://openalex.org/I20121455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082075598","display_name":"Reinhold Haeb\u2010Umbach","orcid":"https://orcid.org/0000-0001-9468-7330"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Reinhold Haeb-Umbach","raw_affiliation_strings":["Paderborn University,Paderborn,Germany"],"affiliations":[{"raw_affiliation_string":"Paderborn University,Paderborn,Germany","institution_ids":["https://openalex.org/I206945453"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5049869565"],"corresponding_institution_ids":["https://openalex.org/I206945453"],"apc_list":null,"apc_paid":null,"fwci":1.5051,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78075889,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"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/T10860","display_name":"Speech and Audio Processing","score":0.9634000062942505,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9634000062942505,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9427000284194946,"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/computer-science","display_name":"Computer science","score":0.7122732400894165},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6747595071792603},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6496836543083191},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.6472573280334473},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4838525354862213},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13692951202392578}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7122732400894165},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6747595071792603},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6496836543083191},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.6472573280334473},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4838525354862213},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13692951202392578},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888012","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888012","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/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1994997260","https://openalex.org/W2084706776","https://openalex.org/W2102840509","https://openalex.org/W2135601293","https://openalex.org/W2176409853","https://openalex.org/W2747874407","https://openalex.org/W2951246258","https://openalex.org/W2972359262","https://openalex.org/W2992005611","https://openalex.org/W3047371217","https://openalex.org/W3093575194","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221167580","https://openalex.org/W4306840934","https://openalex.org/W4323896824","https://openalex.org/W4372270801","https://openalex.org/W4372270835","https://openalex.org/W4385823191","https://openalex.org/W4390912423","https://openalex.org/W4391021529","https://openalex.org/W4392903423","https://openalex.org/W4400165212","https://openalex.org/W4402111251","https://openalex.org/W6610566761","https://openalex.org/W6749555683","https://openalex.org/W6752307458","https://openalex.org/W6755056417","https://openalex.org/W6782364052","https://openalex.org/W6796464841","https://openalex.org/W6805710207","https://openalex.org/W6862112264","https://openalex.org/W6864326080"],"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":{"While":[0],"expressive":[1],"speech":[2,40,60],"synthesis":[3],"or":[4,12,22,64],"voice":[5,31,65,83,113],"conversion":[6],"systems":[7],"mainly":[8],"focus":[9],"on":[10,85],"controlling":[11],"manipulating":[13,111],"abstract":[14],"prosodic":[15],"characteristics":[16],"of":[17,29,46,97],"speech,":[18],"such":[19],"as":[20],"emotion":[21],"accent,":[23],"we":[24,70],"here":[25],"address":[26],"the":[27,107,136],"control":[28],"perceptual":[30,82],"qualities":[32],"(PVQs)":[33],"recognized":[34],"by":[35,110],"phonetic":[36],"experts,":[37],"which":[38],"are":[39],"properties":[41],"at":[42],"a":[43,55,72,77,86],"lower":[44],"level":[45],"abstraction.":[47],"The":[48,132],"ability":[49],"to":[50,80],"manipulate":[51],"PVQs":[52],"can":[53],"be":[54],"valuable":[56],"tool":[57],"for":[58,126,141],"teaching":[59],"pathologists":[61],"in":[62],"training":[63],"actors.":[66],"In":[67],"this":[68],"paper,":[69],"integrate":[71],"Conditional":[73],"Continuous-Normalizing-Flow-based":[74],"method":[75],"into":[76],"Text-to-Speech":[78],"system":[79,93],"modify":[81],"attributes":[84],"continuous":[87],"scale.":[88],"Unlike":[89],"previous":[90],"approaches,":[91],"our":[92],"avoids":[94],"direct":[95],"manipulation":[96],"acoustic":[98],"correlates":[99],"and":[100,118,128,139],"instead":[101],"learns":[102],"from":[103],"examples.":[104],"We":[105],"demonstrate":[106],"system's":[108,137],"capability":[109],"four":[112],"qualities:":[114],"Roughness,":[115],"breathiness,":[116],"resonance":[117],"weight.":[119],"Phonetic":[120],"experts":[121],"evaluated":[122],"these":[123],"modifications,":[124],"both":[125,135],"seen":[127],"unseen":[129],"speaker":[130],"conditions.":[131],"results":[133],"highlight":[134],"strengths":[138],"areas":[140],"improvement.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}
