{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T10:30:30Z","timestamp":1769077830076,"version":"3.49.0"},"reference-count":93,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Institute of Information and Communications Technology Planning and Evaluation (IITP) through Korean Government","award":["RS-2025-02283048"],"award-info":[{"award-number":["RS-2025-02283048"]}]},{"name":"Developing the Next-Generation General AI with Reliability, Ethics, and Adaptability","award":["IITP-2025-RS-2023-00255968"],"award-info":[{"award-number":["IITP-2025-RS-2023-00255968"]}]},{"name":"Artificial Intelligence Convergence Innovation Human Resources Development","award":["RS-2021-II212068"],"award-info":[{"award-number":["RS-2021-II212068"]}]},{"name":"Artificial Intelligence Innovation Hub","award":["RS-2019-II190079"],"award-info":[{"award-number":["RS-2019-II190079"]}]},{"name":"Artificial Intelligence Graduate School Program","award":["IITP-2025-RS-2025-02304828"],"award-info":[{"award-number":["IITP-2025-RS-2025-02304828"]}]},{"name":"Artificial Intelligence Star Fellowship Support Program to Nurture the Best Talents"},{"name":"Artificial Intelligence Industrial Convergence Cluster Development Project"},{"name":"Ministry of Science and ICT (MSIT), South Korea, Gwangju Metropolitan City"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tnnls.2025.3584944","type":"journal-article","created":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T17:44:46Z","timestamp":1752255886000},"page":"18422-18436","source":"Crossref","is-referenced-by-count":7,"title":["HierSpeech++: Bridging the Gap Between Semantic and Acoustic Representation of Speech by Hierarchical Variational Inference for Zero-Shot Speech Synthesis"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8925-4474","authenticated-orcid":false,"given":"Sang-Hoon","family":"Lee","sequence":"first","affiliation":[{"name":"Department of Software and Computer Engineering, Department of Artificial Intelligence, Ajou University, Suwon-si, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2390-7628","authenticated-orcid":false,"given":"Ha-Yeong","family":"Choi","sequence":"additional","affiliation":[{"name":"Gen AI Lab, KT Corporation, Seoul, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2287-9111","authenticated-orcid":false,"given":"Seung-Bin","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, Korea University, Seoul, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6249-4996","authenticated-orcid":false,"given":"Seong-Whan","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, Korea University, Seoul, South Korea"}]}],"member":"263","reference":[{"key":"ref1","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref2","first-page":"1","article-title":"HierSpeech: Bridging the gap between text and speech by hierarchical variational inference using self-supervised representations for speech synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lee"},{"key":"ref3","first-page":"1","article-title":"Diffusion-based voice conversion with fast maximum likelihood sampling scheme","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Popov"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29740"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-817"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLPRO.2025.3533362"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2326"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1608"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3047262"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref13","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2023","journal-title":"Trans. Mach. Learn. Research"},{"key":"ref14","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023","journal-title":"arXiv:2301.02111"},{"key":"ref15","article-title":"HiFi-codec: Group-residual vector quantization for high fidelity audio codec","author":"Yang","year":"2023","journal-title":"arXiv:2305.02765"},{"key":"ref16","first-page":"1","article-title":"High-fidelity audio compression with improved RVQGAN","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00618"},{"key":"ref18","article-title":"Make-A-voice: Unified voice synthesis with discrete representation","author":"Huang","year":"2023","journal-title":"arXiv:2305.19269"},{"key":"ref19","article-title":"SoundStorm: Efficient parallel audio generation","author":"Borsos","year":"2023","journal-title":"arXiv:2305.09636"},{"key":"ref20","article-title":"UniAudio: An audio foundation model toward universal audio generation","author":"Yang","year":"2023","journal-title":"arXiv:2310.00704"},{"key":"ref21","first-page":"1","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Ren"},{"key":"ref22","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2020","journal-title":"arXiv:2006.04558"},{"key":"ref23","first-page":"8067","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":"ref24","article-title":"NaturalSpeech: End-to-end text to speech synthesis with human-level quality","author":"Tan","year":"2022","journal-title":"arXiv:2205.04421"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2984091"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-225"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10797"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-489"},{"key":"ref29","article-title":"NANSY++: Unified voice synthesis with neural analysis and synthesis","author":"Choi","year":"2022","journal-title":"arXiv:2211.09407"},{"key":"ref30","article-title":"Mega-TTS 2: Boosting prompting mechanisms for zero-shot speech synthesis","author":"Jiang","year":"2023","journal-title":"arXiv:2307.07218"},{"key":"ref31","first-page":"8599","article-title":"Grad-TTS: A diffusion probabilistic model for text-to-speech","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Popov"},{"key":"ref32","first-page":"11119","article-title":"Guided-TTS: A diffusion model for text-to-speech via classifier guidance","volume-title":"Proc. Int. Conf.  Mach. Learn.","author":"Kim"},{"key":"ref33","article-title":"Guided-TTS 2: A diffusion model for high-quality adaptive text-to-speech with untranscribed data","author":"Kim","year":"2022","journal-title":"arXiv:2205.15370"},{"key":"ref34","article-title":"NaturalSpeech 2: Latent diffusion models are natural and zero-shot speech and singing synthesizers","author":"Shen","year":"2023","journal-title":"arXiv:2304.09116"},{"key":"ref35","article-title":"HiddenSinger: High-quality singing voice synthesis via neural audio codec and latent diffusion models","author":"Hwang","year":"2023","journal-title":"arXiv:2306.06814"},{"key":"ref36","article-title":"StyleTTS 2: Towards human-level text-to-speech through style diffusion and adversarial training with large speech language models","author":"Aaron Li","year":"2023","journal-title":"arXiv:2306.07691"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2235"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1392"},{"key":"ref39","first-page":"1","article-title":"DiTTo-TTS: Diffusion transformers for scalable text-to-speech without domain-specific factors","volume-title":"Proc. 30th Int. Conf. Learn. Represent.","author":"Lee"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612061"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681044"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3362\/0262-8104.2002.009"},{"key":"ref43","first-page":"1","article-title":"P-flow: A fast and data-efficient zero-shot TTS through speech prompting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kim"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832320"},{"key":"ref45","article-title":"F5-TTS: A fairytaler that fakes fluent and faithful speech with flow matching","author":"Chen","year":"2024","journal-title":"arXiv:2410.06885"},{"key":"ref46","article-title":"CosyVoice 2: Scalable streaming speech synthesis with large language models","author":"Du","year":"2024","journal-title":"arXiv:2412.10117"},{"key":"ref47","article-title":"MegaTTS 3: Sparse alignment enhanced latent diffusion transformer for zero-shot speech synthesis","author":"Jiang","year":"2025","journal-title":"arXiv:2502.18924"},{"key":"ref48","first-page":"1","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Jia"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3335119"},{"key":"ref50","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Skerry-Ryan"},{"key":"ref51","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683501"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17559"},{"key":"ref54","first-page":"7748","article-title":"Meta-stylespeech: Multi-speaker adaptive text-to-speech generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Min"},{"key":"ref55","first-page":"1","article-title":"Generspeech: Towards style transfer for generalizable out-of-domain text-to-speech","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747388"},{"key":"ref57","article-title":"AdaSpeech: Adaptive text to speech for custom voice","author":"Chen","year":"2021","journal-title":"arXiv:2103.00993"},{"key":"ref58","first-page":"2709","article-title":"YourTTS: Towards zero-shot multi-speaker TTS and zero-shot voice conversion for everyone","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Casanova"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095515"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3308374"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3402088"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096285"},{"key":"ref63","article-title":"PromptTTS 2: Describing and generating voices with text prompt","author":"Leng","year":"2023","journal-title":"arXiv:2309.02285"},{"key":"ref64","first-page":"12449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Baevski"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3191677"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3156757"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-143"},{"key":"ref68","article-title":"Scaling speech technology to 1,000+ languages","author":"Pratap","year":"2023","journal-title":"arXiv:2305.13516"},{"key":"ref69","first-page":"16251","article-title":"Neural analysis and synthesis: Reconstructing speech from self-supervised representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"34","author":"Choi"},{"key":"ref70","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":"ref71","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022","journal-title":"arXiv:2210.13438"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-845"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746675"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1905"},{"key":"ref78","article-title":"Superseded-CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit","author":"Veaux","year":"2017"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.5743729"},{"key":"ref80","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Loshchilov"},{"key":"ref81","article-title":"Chunked autoregressive GAN for conditional waveform synthesis","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Morrison"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413948"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1064"},{"key":"ref86","first-page":"5210","article-title":"AutoVC: Zero-shot voice style transfer with only autoencoder loss","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qian"},{"key":"ref87","first-page":"294","article-title":"VoiceMixer: Adversarial voice style mixup","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Lee"},{"key":"ref88","first-page":"1","article-title":"Maskgct: Zero-shot text-to-speech with masked generative codec transformer","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref89","article-title":"Seed-TTS: A family of high-quality versatile speech generation models","author":"Anastassiou","year":"2024","journal-title":"arXiv:2406.02430"},{"key":"ref90","article-title":"FireRedTTS: A foundation Text-To-Speech framework for industry-level generative speech applications","author":"Guo","year":"2024","journal-title":"arXiv:2409.03283"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-45"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095103"},{"key":"ref93","article-title":"AudioSR: Versatile audio super-resolution at scale","author":"Liu","year":"2023","journal-title":"arXiv:2309.07314"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11195929\/11078430.pdf?arnumber=11078430","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T17:39:37Z","timestamp":1759945177000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11078430\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":93,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3584944","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}