{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T23:16:14Z","timestamp":1784675774793,"version":"3.55.0"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3402088","type":"journal-article","created":{"date-parts":[[2024,5,20]],"date-time":"2024-05-20T17:30:53Z","timestamp":1716226253000},"page":"2913-2925","source":"Crossref","is-referenced-by-count":61,"title":["InstructTTS: Modelling Expressive TTS in Discrete Latent Space With Natural Language Style Prompt"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8905-224X","authenticated-orcid":false,"given":"Dongchao","family":"Yang","sequence":"first","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0943-2446","authenticated-orcid":false,"given":"Songxiang","family":"Liu","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1695-9000","authenticated-orcid":false,"given":"Rongjie","family":"Huang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8712-9176","authenticated-orcid":false,"given":"Chao","family":"Weng","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4427-3532","authenticated-orcid":false,"given":"Helen","family":"Meng","sequence":"additional","affiliation":[{"name":"Chinese University of Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref2","first-page":"1","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ren","year":"2020"},{"key":"ref3","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","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1426"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-29516-5_5"},{"key":"ref6","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","year":"2018"},{"key":"ref7","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","year":"2018"},{"key":"ref8","first-page":"4485","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","year":"2018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-645"},{"key":"ref10","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"},{"key":"ref11","article-title":"MusicLM: Generating music from text","year":"2023"},{"key":"ref12","first-page":"7748","article-title":"Meta-StyleSpeech: Multi-speaker adaptive text-to-speech generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Min","year":"2021"},{"key":"ref13","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3149712"},{"key":"ref15","first-page":"6309","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Van Den Oord","year":"2017"},{"key":"ref16","first-page":"14866","article-title":"Generating diverse high-fidelity images with VQ-VAE-2","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Razavi","year":"2019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref18","first-page":"1","article-title":"VQ-Wav2Vec: Self-supervised learning of discrete speech representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Baevski","year":"2019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref20","article-title":"High fidelity neural audio compression","author":"Dfossez","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref22","first-page":"1","article-title":"Taming visually guided sound generation","volume-title":"Proc. Brit. Mach. Vis. Conf. (BMVC)","author":"Iashin","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268730"},{"key":"ref24","article-title":"HiFi-Codec: Group-residual vector quantization for high fidelity audio codec","author":"Yang","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1461"},{"key":"ref26","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","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1774"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3233324"},{"key":"ref29","first-page":"10970","article-title":"GenerSpeech: Towards style transfer for generalizable out-of-domain text-to-speech","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Huang","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-947"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-465"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096285"},{"key":"ref33","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Dhariwal","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref35","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol","year":"2022"},{"key":"ref36","first-page":"3518","article-title":"ImageBART: Bidirectional context with multinomial diffusion for autoregressive image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Esser","year":"2021"},{"key":"ref37","first-page":"4328","article-title":"Diffusion-LM improves controllable text generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Li","year":"2022"},{"key":"ref38","first-page":"1","article-title":"DiffuSeq: Sequence to sequence text generation with diffusion models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gong","year":"2023"},{"key":"ref39","first-page":"1","article-title":"DiffWave: A versatile diffusion model for audio synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kong","year":"2020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-469"},{"key":"ref41","first-page":"13916","article-title":"Make-an-audio: Text-to-audio generation with prompt-enhanced diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Huang","year":"2023"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref43","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein","year":"2015"},{"key":"ref44","first-page":"12454","article-title":"Argmax flows and multinomial diffusion: Learning categorical distributions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Hoogeboom","year":"2021"},{"key":"ref45","first-page":"17981","article-title":"Structured denoising diffusion models in discrete state-spaces","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Austin","year":"2021"},{"key":"ref46","first-page":"1","article-title":"RoBERTa: A robustly optimized bert pretraining approach","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu","year":"2019"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"ref48","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9979989"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.202"},{"key":"ref51","first-page":"531","article-title":"Mutual information neural estimation","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Belghazi","year":"2018"},{"key":"ref52","first-page":"1779","article-title":"CLUB: A contrastive log-ratio upper bound of mutual information","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cheng","year":"2020"},{"key":"ref53","article-title":"A survey on neural speech synthesis","author":"Tan","year":"2021"},{"key":"ref54","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","year":"2020"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-489"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref58","first-page":"1","article-title":"Classifier-free diffusion guidance","volume-title":"Proc. Workshop Deep Generative Models Downstream Appl.","author":"Ho","year":"2022"},{"key":"ref59","article-title":"Improved vector quantized diffusion models","author":"Tang","year":"2022"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-755"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref63","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26488"},{"key":"ref65","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.09.003"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960497"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.02.010"},{"key":"ref72","first-page":"1","article-title":"DiffGAN-TTS: High-fidelity and efficient text-to-speech with denoising diffusion GANs","volume-title":"Proc. Int. Conf. Mach. Learn. Workshop","author":"Liu","year":"2022"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1001\/archpsyc.1986.01800030098011"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780195169157.003.0016"},{"key":"ref75","first-page":"12449","article-title":"Wav2Vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Baevski","year":"2020"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10534832.pdf?arnumber=10534832","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T20:52:54Z","timestamp":1719348774000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10534832\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3402088","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}