{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T05:39:56Z","timestamp":1774589996535,"version":"3.50.1"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888012","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Speech Synthesis along Perceptual Voice Quality Dimensions"],"prefix":"10.1109","author":[{"given":"Frederik","family":"Rautenberg","sequence":"first","affiliation":[{"name":"Paderborn University,Paderborn,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Kuhlmann","sequence":"additional","affiliation":[{"name":"Paderborn University,Paderborn,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fritz","family":"Seebauer","sequence":"additional","affiliation":[{"name":"Bielefeld University,Bielefeld,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jana","family":"Wiechmann","sequence":"additional","affiliation":[{"name":"Bielefeld University,Bielefeld,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Petra","family":"Wagner","sequence":"additional","affiliation":[{"name":"Bielefeld University,Bielefeld,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Reinhold","family":"Haeb-Umbach","sequence":"additional","affiliation":[{"name":"Paderborn University,Paderborn,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747442"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/SpeechProsody.2024-208"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097200"},{"key":"ref4","first-page":"4693","article-title":"Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron","volume-title":"International Conference on Machine Learning","author":"Skerry-Ryan"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2023.3250266"},{"key":"ref6","article-title":"Daisy-TTS: Simulating Wider Spectrum of Emotions via Prosody Embedding Decomposition","author":"Chevi","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-8403-5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/11520153_4"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2216"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389745"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1044\/1058-0360(2008\/08-0017)"},{"key":"ref12","article-title":"ANGUS: Real-Time Manipulation of Vocal Roughness for Emotional Speech Transformations","author":"Liuni","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/EEEI.2008.4736577"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415036"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446197"},{"key":"ref16","first-page":"1530","article-title":"Variational Inference with Normalizing Flows","volume-title":"International Conference on Machine Learning","author":"Rezende"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992934"},{"key":"ref18","article-title":"VoiceShop: A Unified Speech-to-Speech Framework for Identity-Preserving Zero-Shot Voice Editing","author":"Anastassiou","year":"2024"},{"key":"ref19","first-page":"2709","article-title":"YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for Everyone","volume-title":"International Conference on Machine Learning","author":"Casanova"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3447648"},{"key":"ref21","article-title":"Neural Ordinary Differential Equations","volume":"31","author":"Chen","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref22","article-title":"FFJORD: Free-Form Continuous Dynamics for Scalable Reversible Generative Models","volume-title":"International Conference on Learning Representations","author":"Grathwohl"},{"key":"ref23","first-page":"5530","article-title":"Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech","volume-title":"International Conference on Machine Learning","author":"Kim"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095370"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1584"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvoice.2020.10.001"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref31","article-title":"ITU-T Rec. P.808, Subjective evaluation of speech quality with a crowdsourcing approach","year":"2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/VCCBC.2020-14"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1972.10481279"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1044\/2022_JSLHR-22-00012"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888012.pdf?arnumber=10888012","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:17Z","timestamp":1774416197000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888012\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888012","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}