{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:20:26Z","timestamp":1774419626272,"version":"3.50.1"},"reference-count":22,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890697","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:56:59Z","timestamp":1741787819000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Can We \"Cherry-Pick\"? Investigating Multiple Renditions from a Generative Speech Synthesis Model"],"prefix":"10.1109","author":[{"given":"Adaeze","family":"Adigwe","sequence":"first","affiliation":[{"name":"University of Edinburgh,The Centre for Speech Technology Research,Edinburgh,UK"}]},{"given":"Sarenne","family":"Wallbridge","sequence":"additional","affiliation":[{"name":"University of Edinburgh,The Centre for Speech Technology Research,Edinburgh,UK"}]},{"given":"Zehai","family":"Tu","sequence":"additional","affiliation":[{"name":"Tencent,LightSpeed Studios"}]},{"given":"Catherine","family":"Lai","sequence":"additional","affiliation":[{"name":"University of Edinburgh,The Centre for Speech Technology Research,Edinburgh,UK"}]},{"given":"Simon","family":"King","sequence":"additional","affiliation":[{"name":"University of Edinburgh,The Centre for Speech Technology Research,Edinburgh,UK"}]}],"member":"263","reference":[{"key":"ref1","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"International conference on machine learning","author":"Wang"},{"key":"ref2","first-page":"1336","article-title":"On generative spoken language modeling from raw audio","volume":"9","author":"Lakhotia","year":"2021","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref4","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.673"},{"key":"ref6","article-title":"Natural language guidance of high-fidelity text-to-speech with synthetic annotations","author":"Lyth","year":"2024"},{"key":"ref7","article-title":"Base tts: Lessons from building a billion-parameter text-to-speech model on 100k hours of data","author":"Lajszczak","year":"2024"},{"key":"ref8","article-title":"Evaluating text-to-speech synthesis from a large discrete token-based speech language model","author":"Wang","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.11"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1658"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1951"},{"key":"ref12","article-title":"Parler-tts","author":"Lacombe","year":"2024"},{"key":"ref13","article-title":"Jenny tts dataset","year":"2024","journal-title":"A high-quality, varied ~30hr voice dataset suitable for training a TTS model"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10890055"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096680"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414878"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.2307\/2334029"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2023-2"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-26"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1193"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-781"}],"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\/10890697.pdf?arnumber=10890697","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:49Z","timestamp":1774416229000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890697\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890697","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}