{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:28:13Z","timestamp":1775230093220,"version":"3.50.1"},"reference-count":54,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003816","name":"Huawei Technologies","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003816","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006785","name":"Google","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006785","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832178","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"766-773","source":"Crossref","is-referenced-by-count":5,"title":["TTSDS - Text-to-Speech Distribution Score"],"prefix":"10.1109","author":[{"given":"Christoph","family":"Minixhofer","sequence":"first","affiliation":[{"name":"The University of Edinburgh Centre for Speech Technology Research"}]},{"given":"Ond\u0159ej","family":"Klejch","sequence":"additional","affiliation":[{"name":"The University of Edinburgh Centre for Speech Technology Research"}]},{"given":"Peter","family":"Bell","sequence":"additional","affiliation":[{"name":"The University of Edinburgh Centre for Speech Technology Research"}]}],"member":"263","reference":[{"key":"ref1","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022","journal-title":"arXiv:2210.13438"},{"key":"ref2","article-title":"Natural language guidance of high-fidelity text-to-speech with synthetic annotations","author":"Lyth","year":"2024","journal-title":"arXiv:2402.01912"},{"key":"ref3","article-title":"VALL-E 2: Neural codec language models are human parity zero-shot text to speech synthesizers","author":"Chen","year":"2024","journal-title":"arXiv:2406.05370"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2016"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10633"},{"key":"ref6","article-title":"Pheme: Efficient and conversational speech generation","author":"Budzianowski","year":"2024","journal-title":"arXiv:2401.02839"},{"key":"ref7","article-title":"StyleTTS 2: Towards human-level text-to-speech through style diffusion and adversarial training with large speech language models","author":"Li","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1978"},{"key":"ref9","article-title":"Text to speech arena","author":"mrfakename","year":"2024"},{"key":"ref10","article-title":"GANs trained by a two timescale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017"},{"key":"ref11","article-title":"A spectral energy distance for parallel speech synthesis","author":"Gritsenko","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26488"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w18-5446"},{"key":"ref14","article-title":"SuperGLUE: A stickier benchmark for general-purpose language understanding systems","author":"Wang","year":"2019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00266"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4020-5817-2_2"},{"key":"ref18","article-title":"Multispeaker modeling and speaker adaptation for DNNbased TTS synthesis","author":"Fan","year":"2015","journal-title":"ICASSP"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1250\/ast.e24.12"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2003.12.001"},{"key":"ref22","article-title":"VoiceFixer: Toward general speech restoration with neural vocoder","author":"Liu","year":"2021","journal-title":"arXiv:2109.13731"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2008-644"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096626"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref29","article-title":"Masked prosody model","author":"Wallbridge","year":"2023"},{"key":"ref30","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020"},{"key":"ref31","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2023","journal-title":"ICML"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref33","article-title":"Markov processes over denumerable products of spaces, describing large systems of automata","author":"Vaserstein","year":"1969","journal-title":"Problemy Peredachi Informatsii"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2219"},{"key":"ref35","article-title":"Sliced-wasserstein autoencoder: An embarrassingly simple generative model","author":"Kolouri","year":"2018","journal-title":"arXiv:1804.01947"},{"key":"ref36","article-title":"The blizzard challenge 2008","volume-title":"The Blizzard Challenge Workshop","author":"King"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Blizzard.2013-1"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Blizzard.2021-1"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413889"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1584"},{"key":"ref43","article-title":"The LJ speech dataset","author":"Ito","year":"2017"},{"key":"ref44","article-title":"English multi-speaker corpus for cstr voice cloning toolkit","author":"Yamagishi","year":"2013"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref46","article-title":"HiFi++: a unified framework for neural vocoding, bandwidth extension and speech enhancement","author":"Andreev","year":"2022","journal-title":"arXiv:2203.13086"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-970"},{"key":"ref49","article-title":"NaturalSpeech 3: Zero-shot speech synthesis with factorized codec and diffusion models","author":"Ju","year":"2024","journal-title":"arXiv:2403.03100"},{"key":"ref50","article-title":"OpenVoice: Versatile instant voice cloning","author":"Qin","year":"2023","journal-title":"arXiv:2312.01479"},{"key":"ref51","article-title":"WhisperSpeech","author":"C\u0142apa","year":"2024"},{"key":"ref52","volume-title":"Parler TTS","author":"Lacombe","year":"2024"},{"key":"ref53","article-title":"Vokan","year":"2024"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.673"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","location":"Macao","start":{"date-parts":[[2024,12,2]]},"end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832178.pdf?arnumber=10832178","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T07:41:49Z","timestamp":1737099709000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832178\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832178","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}