{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:13:16Z","timestamp":1763190796759,"version":"3.45.0"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11227557","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["TV-MDiff: A Zero-Shot Text-To-Speech and Zero-Shot Voice Conversion System with Mamba-Based Diffusion Model"],"prefix":"10.1109","author":[{"given":"Zhihua","family":"Huang","sequence":"first","affiliation":[{"name":"Xinjiang University,School of Computer Science and Technology,Urumqi,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ke","family":"Chen","sequence":"additional","affiliation":[{"name":"Xinjiang University,School of Computer Science and Technology,Urumqi,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yonghong","family":"Yan","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"7748","article-title":"Meta-stylespeech: Multi-speaker adaptive text-to-speech generation","volume-title":"International Conference on Machine Learning","author":"Min"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/ICASSP43922.2022.9746875"},{"volume-title":"International Conference on Learning Representations","author":"Popov","article-title":"Diffusion-based voice conversion with fast maximum likelihood sampling scheme","key":"ref3"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.21437\/Interspeech.2023-817"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1609\/aaai.v38i16.29740"},{"key":"ref6","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":"ref7","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"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.21437\/Interspeech.2023-368"},{"key":"ref9","first-page":"16624","article-title":"Hierspeech: Bridging the gap between text and speech by hierarchical variational inference using self-supervised representations for speech synthesis","volume":"35","author":"Lee","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/ICASSP48485.2024.10446855"},{"year":"2023","author":"Gu","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","key":"ref11"},{"key":"ref12","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"volume-title":"International Conference on Learning Representations","author":"Song","article-title":"Denoising diffusion implicit models","key":"ref13"},{"key":"ref14","first-page":"8599","article-title":"Gradtts: A diffusion probabilistic model for text-to-speech","volume-title":"International Conference on Machine Learning","author":"Popov"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1145\/3503161.3547855"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/icassp49357.2023.10096710"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1609\/aaai.v38i17.29932"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.48550\/arXiv.1609.03499"},{"volume-title":"International Conference on Learning Representations","author":"Kong","article-title":"Diffwave: A versatile diffusion model for audio synthesis","key":"ref19"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.21437\/interspeech.2020-3015"},{"volume-title":"International Conference on Learning Representations","author":"Ren","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","key":"ref21"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.21437\/Interspeech.2021-475"},{"volume-title":"International Conference on Learning Representations","author":"Gu","article-title":"Efficiently modeling long sequences with structured state spaces","key":"ref23"},{"key":"ref24","first-page":"572","article-title":"Combining recurrent, convolutional, and continuous-time models with linear state space layers","volume":"34","author":"Gu","year":"2021","journal-title":"Advances in neural information processing systems"},{"volume-title":"The Eleventh International Conference on Learning Representations","author":"Smith","article-title":"Simplified state space layers for sequence modeling","key":"ref25"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1007\/978-3-031-72649-1_13"},{"volume-title":"Forty-first International Conference on Machine Learning","author":"Zhu","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","key":"ref27"},{"year":"2024","author":"Liu","article-title":"Vmamba: Visual state space model","key":"ref28"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.48550\/ARXIV.1706.03762"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1109\/CVPR52729.2023.02142"},{"year":"2016","author":"Hendrycks","article-title":"Gaussian error linear units (gelus)","key":"ref31"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1109\/ICASSP39728.2021.9415079"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1109\/ICASSP43922.2022.9746484"},{"year":"2020","author":"Heo","article-title":"Clova baseline system for the voxceleb speaker recognition challenge 2020","key":"ref34"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.21437\/Interspeech.2017-1386"},{"volume-title":"International Conference on Learning Representations","author":"Salimans","article-title":"Progressive distillation for fast sampling of diffusion models","key":"ref36"},{"doi-asserted-by":"publisher","key":"ref37","DOI":"10.21437\/Interspeech.2019-2441"},{"doi-asserted-by":"publisher","key":"ref38","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"year":"2016","author":"Veaux","article-title":"Superseded-cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit","key":"ref39"},{"doi-asserted-by":"publisher","key":"ref40","DOI":"10.21437\/Interspeech.2021-755"},{"year":"2017","article-title":"Chinese standard mandarin speech corpus","key":"ref41"},{"key":"ref42","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref43","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford"},{"doi-asserted-by":"publisher","key":"ref44","DOI":"10.1109\/ICASSP43922.2022.9746806"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11227557.pdf?arnumber=11227557","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:10:15Z","timestamp":1763190615000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11227557\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11227557","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}