{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:48:02Z","timestamp":1730231282568,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10448195","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11266-11270","source":"Crossref","is-referenced-by-count":0,"title":["DurIAN-E 2: Duration Informed Attention Network with Adaptive Variational Autoencoder and Adversarial Learning for Expressive Text-to-Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Yu","family":"Gu","sequence":"first","affiliation":[{"name":"Tencent AI Lab"}]},{"given":"Qiushi","family":"Zhu","sequence":"additional","affiliation":[{"name":"Tencent AI Lab"}]},{"given":"Guangzhi","family":"Lei","sequence":"additional","affiliation":[{"name":"Tencent AI Lab"}]},{"given":"Chao","family":"Weng","sequence":"additional","affiliation":[{"name":"Tencent AI Lab"}]},{"given":"Dan","family":"Su","sequence":"additional","affiliation":[{"name":"Tencent AI Lab"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1426"},{"key":"ref2","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"International Conference on Machine Learning","author":"Wang"},{"key":"ref3","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with Tacotron","volume-title":"international conference on machine learning","author":"Skerry-Ryan"},{"article-title":"DurIAN-E: Duration informed attention network for expressive text-to-speech synthesis","year":"2023","author":"Gu","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2968"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"article-title":"StyleTTS: A style-based generative model for natural and diverse text-to-speech synthesis","year":"2022","author":"Li","key":"ref7"},{"article-title":"Simple recurrence improves masked language models","year":"2022","author":"Lei","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref10","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1506"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-414"},{"key":"ref13","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":"ref14","article-title":"Glow-TTS: A generative Flow for text-to-speech via monotonic alignment search","volume":"33","author":"Kim","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"BigVGAN: A universal neural vocoder with large-scale training","volume-title":"The Eleventh International Conference on Learning Representations","author":"Lee","key":"ref15"},{"article-title":"Density estimation using Real NVP","volume-title":"International Conference on Learning Representations","author":"Dinh","key":"ref16"},{"key":"ref17","first-page":"125","article-title":"WaveNet: A generative model for raw audio","volume-title":"9th ISCA Speech Synthesis Workshop","author":"Van den Oord"},{"key":"ref18","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"},{"article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","volume-title":"NeurIPS","author":"Kumar","key":"ref19"},{"article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","volume-title":"International Conference on Learning Representations","author":"Ren","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21350"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10448195.pdf?arnumber=10448195","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T06:56:57Z","timestamp":1722581817000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448195\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448195","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}