{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T21:15:19Z","timestamp":1765228519963,"version":"3.46.0"},"reference-count":28,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"EU Horizon Project AI4TRUST","award":["101070190"],"award-info":[{"award-number":["101070190"]}]},{"name":"Ministry of Research, Innovation and Digitization, CCCDI\u2014UEFISCDI","award":["PN-IV-P7-7.1-PTE-2024-0546, within PNCDI IV"],"award-info":[{"award-number":["PN-IV-P7-7.1-PTE-2024-0546, within PNCDI IV"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3637322","type":"journal-article","created":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T19:05:14Z","timestamp":1764183914000},"page":"203415-203428","source":"Crossref","is-referenced-by-count":0,"title":["How Open Is Open TTS? A Practical Evaluation of Open Source TTS Tools"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4962-2834","authenticated-orcid":false,"given":"Teodora","family":"R\u0103gman","sequence":"first","affiliation":[{"name":"POLITEHNICA Bucharest, Bucharest, Romania"}]},{"given":"Adrian","family":"Bogdan St\u00e2nea","sequence":"additional","affiliation":[{"name":"Technical University of Cluj-Napoca, Cluj-Napoca, Romania"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8711-3854","authenticated-orcid":false,"given":"Horia","family":"Cucu","sequence":"additional","affiliation":[{"name":"POLITEHNICA Bucharest, Bucharest, Romania"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2894-5770","authenticated-orcid":false,"given":"Adriana","family":"Stan","sequence":"additional","affiliation":[{"name":"POLITEHNICA Bucharest, Bucharest, Romania"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A survey on neural speech synthesis","author":"Tan","year":"2021","journal-title":"arXiv:2106.15561"},{"key":"ref2","first-page":"1","article-title":"Towards controllable speech synthesis in the era of large language models: A survey","volume-title":"Proc. EMNLP","author":"Xie"},{"key":"ref3","article-title":"A survey on audio diffusion models: Text to speech synthesis and enhancement in generative AI","author":"Zhang","year":"2023","journal-title":"arXiv:2303.13336"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48175\/IJARSCT-1400"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref6","first-page":"1","article-title":"High fidelity neural audio compression","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"D\u00e9fossez"},{"key":"ref7","article-title":"Natural language guidance of high-fidelity text-to-speech with synthetic annotations","author":"Lyth","year":"2024","journal-title":"arXiv:2402.01912"},{"key":"ref8","first-page":"27980","article-title":"High-fidelity audio compression with improved RVQGAN","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Kumar"},{"key":"ref9","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","volume":"37","author":"Sohl-Dickstein"},{"key":"ref10","first-page":"1530","article-title":"Variational inference with normalizing flows","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","volume":"37","author":"Rezende"},{"key":"ref11","first-page":"1","article-title":"WaveGrad: Estimating gradients for waveform generation","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Chen"},{"key":"ref12","first-page":"11119","article-title":"Guided-TTS: A diffusion model for text-to-speech via classifier guidance","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"162","author":"Kim"},{"key":"ref13","first-page":"4157","article-title":"FastDiff: A fast conditional diffusion model for high-quality speech synthesis","volume-title":"Proc. 31st Int. Joint Conf. Artif. Intell.","author":"Huang"},{"key":"ref14","first-page":"1","article-title":"DiffWave: A versatile diffusion model for audio synthesis","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Kong"},{"key":"ref15","first-page":"8599","article-title":"Grad-TTS: A diffusion probabilistic model for text-to-speech","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Popov"},{"key":"ref16","article-title":"Flowtron: An autoregressive flow-based generative network for text-to-speech synthesis","author":"Valle","year":"2020","journal-title":"arXiv:2005.05957"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054484"},{"key":"ref18","first-page":"13963","article-title":"PortaSpeech: Portable and high-quality generative text-to-speech","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Ren"},{"key":"ref19","first-page":"15829","article-title":"Glow-TTS: A generative flow for text-to-speech via monotonic alignment search","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kim"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448291"},{"key":"ref21","first-page":"6879","article-title":"VITS: Variational inference with adversarial learning for end-to-end text-to-speech","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Kim"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413889"},{"key":"ref23","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kong"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SPED.2017.7990428"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref26","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","volume":"202","author":"Radford"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096680"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11269795.pdf?arnumber=11269795","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T18:42:10Z","timestamp":1765219330000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11269795\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3637322","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}