{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T13:44:32Z","timestamp":1765547072279,"version":"3.28.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10094298","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":8,"title":["Text-To-Speech Synthesis Based on Latent Variable Conversion Using Diffusion Probabilistic Model and Variational Autoencoder"],"prefix":"10.1109","author":[{"given":"Yusuke","family":"Yasuda","sequence":"first","affiliation":[{"name":"Nagoya University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[{"name":"Nagoya University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10045"},{"key":"ref12","first-page":"11119","article-title":"Guided-TTS: A diffusion model for text-to-speech via classifier guidance","volume":"162","author":"kim","year":"2022","journal-title":"ICML"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2571"},{"key":"ref14","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2014","journal-title":"ICLRE"},{"key":"ref31","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","volume":"9351","author":"ronneberger","year":"2015","journal-title":"MICCAI (3)"},{"key":"ref30","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume":"abs 2006 4558","author":"ren","year":"2020","journal-title":"CoRR"},{"key":"ref11","article-title":"PriorGrad: Improving conditional denoising diffusion models with data-dependent adaptive prior","author":"lee","year":"2022","journal-title":"ICLRE"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1897"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177730491"},{"key":"ref2","article-title":"Close to human quality TTS with transformer","volume":"abs 1809 8895","author":"li","year":"2018","journal-title":"CoRR"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref17","first-page":"6306","article-title":"Neural discrete representation learning","author":"van den oord","year":"2017","journal-title":"NIPS"},{"key":"ref16","article-title":"Hierarchical generative modeling for controllable speech synthesis","author":"hsu","year":"2019","journal-title":"ICLR (Poster)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1757"},{"key":"ref18","article-title":"Semi-supervised generative modeling for controllable speech synthesis","author":"habib","year":"2020","journal-title":"ICLRE"},{"key":"ref24","first-page":"11895","article-title":"Generative modeling by estimating gradients of the data distribution","author":"song","year":"2019","journal-title":"NeurIPS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547855"},{"key":"ref26","first-page":"8599","article-title":"Grad-TTS: A diffusion probabilistic model for text-to-speech","volume":"139","author":"popov","year":"2021","journal-title":"ICML"},{"key":"ref25","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"ramesh","year":"2022","journal-title":"CoRR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10797"},{"key":"ref22","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume":"139","author":"nichol","year":"2021","journal-title":"ICML"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3190672"},{"key":"ref28","article-title":"Glow-TTS: A generative flow for text-to-speech via monotonic alignment search","author":"kim","year":"2020","journal-title":"NeurIPS"},{"key":"ref27","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"2020","journal-title":"NeurIPS"},{"key":"ref29","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NIPS"},{"key":"ref8","article-title":"WaveGrad: Estimating gradients for waveform generation","author":"chen","year":"2021","journal-title":"ICLRE"},{"key":"ref7","article-title":"Denoising diffusion probabilistic models","author":"ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-469"},{"journal-title":"WaveNet A Generative Model for Raw Audio","year":"2016","author":"van den oord","key":"ref4"},{"key":"ref3","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume":"139","author":"kim","year":"2021","journal-title":"ICML"},{"key":"ref6","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc NIPS"},{"key":"ref5","first-page":"1530","article-title":"Variational inference with normalizing flows","author":"rezende","year":"2015","journal-title":"Proc ICML"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10094298.pdf?arnumber=10094298","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T18:57:32Z","timestamp":1700506652000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10094298\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10094298","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}