{"id":"https://openalex.org/W4408354154","doi":"https://doi.org/10.1109/icassp49660.2025.10890772","title":"Precisely Controllable Neural Speech Synthesis","display_name":"Precisely Controllable Neural Speech Synthesis","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354154","doi":"https://doi.org/10.1109/icassp49660.2025.10890772"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890772","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890772","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/A5004916681","display_name":"Paul Konstantin Krug","orcid":"https://orcid.org/0000-0001-8518-8142"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paul Konstantin Krug","raw_affiliation_strings":["Altavo GmbH,Dresden,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Altavo GmbH,Dresden,Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107415025","display_name":"Christoph Wagner","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christoph Wagner","raw_affiliation_strings":["Altavo GmbH,Dresden,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Altavo GmbH,Dresden,Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046141664","display_name":"Peter Birkholz","orcid":"https://orcid.org/0000-0003-0167-8123"},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Peter Birkholz","raw_affiliation_strings":["Technische Universität Dresden,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universität Dresden,Germany","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5116594480","display_name":"Timo Stich","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Timo Stich","raw_affiliation_strings":["Altavo GmbH,Dresden,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Altavo GmbH,Dresden,Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7588,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85586097,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9782999753952026,"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":0.9782999753952026,"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":0.6539159417152405},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4817652702331543},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.454253226518631},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4174625873565674},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2774202227592468}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6539159417152405},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4817652702331543},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.454253226518631},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4174625873565674},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2774202227592468}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890772","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890772","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":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1965378753","https://openalex.org/W1972620250","https://openalex.org/W1995118599","https://openalex.org/W2027933203","https://openalex.org/W2038299421","https://openalex.org/W2064675550","https://openalex.org/W2126289105","https://openalex.org/W2396590251","https://openalex.org/W2696967604","https://openalex.org/W2752796333","https://openalex.org/W2964243274","https://openalex.org/W2972552159","https://openalex.org/W3095410713","https://openalex.org/W3095560934","https://openalex.org/W3097777922","https://openalex.org/W3193311858","https://openalex.org/W3193797593","https://openalex.org/W3205878676","https://openalex.org/W3209984917","https://openalex.org/W4297841848","https://openalex.org/W4317754363","https://openalex.org/W4362654427","https://openalex.org/W4372340876","https://openalex.org/W4372341338","https://openalex.org/W4385823070","https://openalex.org/W4385823163","https://openalex.org/W4385823191","https://openalex.org/W4385823207","https://openalex.org/W4385823333","https://openalex.org/W4398152753","https://openalex.org/W4402111787","https://openalex.org/W4406461588","https://openalex.org/W6639350448","https://openalex.org/W6723840500","https://openalex.org/W6729748113","https://openalex.org/W6777694618","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6796464841","https://openalex.org/W6796730497","https://openalex.org/W6797957363","https://openalex.org/W6847363464","https://openalex.org/W6861507043","https://openalex.org/W6870487644"],"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":{"Recent":[0],"advances":[1],"in":[2,113],"deep":[3,117],"learning":[4],"have":[5],"significantly":[6],"improved":[7],"the":[8,88,95,121,128],"quality":[9,96],"of":[10,23,97,123],"speech":[11,33,84,99,135],"synthesis,":[12,74],"yet":[13,82],"these":[14,59],"models":[15],"often":[16],"suffer":[17],"from":[18,136],"limited":[19],"controllability":[20],"and":[21,38,54,80,116],"lack":[22],"interpretability":[24],"due":[25],"to":[26,101,131],"their":[27],"black-box":[28],"nature.":[29],"In":[30],"contrast,":[31],"articulatory":[32,70,90,115,118,140],"synthesis":[34,55,85],"offers":[35],"fine-grained":[36],"control":[37],"transparency":[39],"by":[40],"simulating":[41],"sound":[42],"production":[43],"based":[44],"on":[45],"vocal":[46],"tract":[47],"geometry,":[48],"though":[49],"it":[50],"struggles":[51],"with":[52],"naturalness":[53],"quality.":[56],"To":[57,120],"bridge":[58],"gaps,":[60],"we":[61],"propose":[62],"a":[63,76,137],"novel":[64],"white-box":[65],"approach":[66],"that":[67],"leverages":[68],"synthetic":[69,139],"trajectories":[71],"for":[72],"neural":[73],"ensuring":[75],"fully":[77],"disentangled,":[78],"interpretable,":[79],"controllable":[81],"high-quality":[83],"process.":[86],"Utilizing":[87],"VocalTractLab":[89],"synthesizer,":[91],"our":[92,124],"method":[93],"allows":[94],"its":[98],"representation":[100],"be":[102],"verified":[103],"through":[104],"physical":[105],"simulation.":[106],"The":[107],"proposed":[108],"system":[109],"achieves":[110],"state-of-the-art":[111],"results":[112],"both":[114],"synthesis.":[119],"best":[122],"knowledge,":[125],"this":[126],"is":[127],"first":[129],"work":[130],"synthesize":[132],"highly":[133],"intelligible":[134],"purely":[138],"latent":[141],"representation.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}