{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:28:11Z","timestamp":1774420091783,"version":"3.50.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888129","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["LEF-TTS: Lightweight and Efficient End-to-End Text-to-Speech Synthesis With Multi-Stream Generator"],"prefix":"10.1109","author":[{"given":"Yan","family":"Shi","sequence":"first","affiliation":[{"name":"Ping An Technology,China"}]},{"given":"Jin","family":"Shi","sequence":"additional","affiliation":[{"name":"Shanghai University of Finance and Economics"}]},{"given":"Minchuan","family":"Chen","sequence":"additional","affiliation":[{"name":"Ping An Technology,China"}]},{"given":"Chenfeng","family":"Miao","sequence":"additional","affiliation":[{"name":"Ping An Technology,China"}]},{"given":"Ming","family":"Fang","sequence":"additional","affiliation":[{"name":"Ping An Technology,China"}]},{"given":"Ning","family":"Cheng","sequence":"additional","affiliation":[{"name":"Ping An Technology,China"}]},{"given":"Shaojun","family":"Wang","sequence":"additional","affiliation":[{"name":"Ping An Technology,China"}]},{"given":"Jing","family":"Xiao","sequence":"additional","affiliation":[{"name":"Ping An Technology,China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A survey on neural speech synthesis","author":"Tan","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref4","first-page":"3165","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume-title":"Proc. Neural Information Processing Systems, NeurIPS","author":"Ren"},{"key":"ref5","first-page":"1","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. International Conference on Learning Representations, ICLR","author":"Ren"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref7","first-page":"14881","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","volume-title":"Proc. Neural Information Processing Systems, NeurIPS","author":"Kumar"},{"key":"ref8","article-title":"Bigvgan: A universal neural vocoder with large-scale training","volume-title":"International Conference on Learning Representations, ICLR","author":"Lee"},{"key":"ref9","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proc. International Conference on Machine Learning, ICML","volume":"139","author":"Kim"},{"key":"ref10","first-page":"1530","article-title":"Variational inference with normalizing flows","volume-title":"Proc. International Conference on Machine Learning, ICML","volume":"37","author":"Rezende"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023322"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414400"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2867"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414403"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094639"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10095296"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1435"},{"key":"ref18","article-title":"Vocos: Closing the gap between time-domain and fourierbased neural vocoders for high-quality audio synthesis","volume-title":"Proc. International Conference on Learning Representations, ICLR","author":"Siuzdak"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3369528"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref21","article-title":"Universal transformers","volume-title":"Proc. International Conference on Learning Representations, ICLR","author":"Dehghani"},{"key":"ref22","first-page":"9099","article-title":"Transformer quality in linear time","volume-title":"Proc. International Conference on Machine Learning, ICML","author":"Hua"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1609.03499"},{"key":"ref24","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. Neural Information Processing Systems 2020, NeurIPS","author":"Kong"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"ref26","first-page":"1","article-title":"Generative adversarial nets","volume-title":"Proc. Neural Information Processing Systems, NeurIPS","volume":"27","author":"Goodfellow"},{"key":"ref27","article-title":"Auto-encoding variational bayes","volume-title":"Proc. International Conference on Learning Representations, ICLR","author":"Kingma"},{"key":"ref28","first-page":"933","article-title":"Language modeling with gated convolutional networks","volume-title":"Proc. International Conference on Machine Learning, ICML","volume":"70","author":"Dauphin"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/asru51503.2021.9688194"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-0601-3_6"},{"key":"ref31","article-title":"The lj speech dataset","author":"Ito","year":"2017"},{"key":"ref32","article-title":"Decoupled weight decay regularization","volume-title":"Proc. International Conference on Learning Representations, ICLR","author":"Loshchilov"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888129.pdf?arnumber=10888129","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:21Z","timestamp":1774416381000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888129\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888129","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}