{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T15:35:50Z","timestamp":1759160150816,"version":"3.28.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,8]],"date-time":"2024-05-08T00:00:00Z","timestamp":1715126400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,8]],"date-time":"2024-05-08T00:00:00Z","timestamp":1715126400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,8]]},"DOI":"10.1109\/cscwd61410.2024.10580278","type":"proceedings-article","created":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T17:21:49Z","timestamp":1720632109000},"page":"1134-1139","source":"Crossref","is-referenced-by-count":1,"title":["EM-TTS: Efficiently Trained Low-Resource Mongolian Lightweight Text-to-Speech"],"prefix":"10.1109","author":[{"given":"Ziqi","family":"Liang","sequence":"first","affiliation":[{"name":"University of Science and Technology of China"}]},{"given":"Haoxiang","family":"Shi","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}]},{"given":"Jiawei","family":"Wang","sequence":"additional","affiliation":[{"name":"Hefei University of Technology"}]},{"given":"Keda","family":"Lu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"99","article-title":"Mongolian text-to-speech system based on deep neural network","volume-title":"National conference on Man-Machine Speech Communication, NCMMSC","author":"Rui"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-443"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178816"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref5","first-page":"3165","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume-title":"Annual Conference on Neural Information Processing Systems, NeurIPS","author":"Ren"},{"article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume-title":"9th International Conference on Learning Representations, ICLR","author":"Ren","key":"ref6"},{"article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Annual Conference on Neural Information Processing Systems, NeurIPS","author":"Kong","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref9","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML","volume":"139","author":"Kim"},{"key":"ref10","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, ICML","volume":"162","author":"Casanova"},{"key":"ref11","article-title":"Naturalspeech: End-to-end text to speech synthesis with human-level quality","author":"Tan","year":"2022","journal-title":"CoRR"},{"key":"ref12","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023","journal-title":"CoRR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00618"},{"key":"ref14","first-page":"8599","article-title":"Gradtts: A diffusion probabilistic model for text-to-speech","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML","volume":"139","author":"Popov"},{"key":"ref15","first-page":"3605","article-title":"Difftts: A denoising diffusion model for text-to-speech","volume-title":"22nd Annual Conference of the International Speech Communication Association, Interspeech","author":"Jeong"},{"key":"ref16","first-page":"11119","article-title":"Guided-tts: A diffusion model for text-tospeech via classifier guidance","volume-title":"International Conference on Machine Learning, ICML","volume":"162","author":"Kim"},{"article-title":"Priorgrad: Improving conditional denoising diffusion models with data-dependent adaptive prior","volume-title":"The Tenth International Conference on Learning Representations, ICLR","author":"Lee","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MSN57253.2022.00156"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ijcnn55064.2022.9892596"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1609.03499"},{"key":"ref21","first-page":"14881","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","volume-title":"Annual Conference on Neural Information Processing Systems, NeurIPS","author":"Kumar"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref23","first-page":"2415","article-title":"Efficient neural audio synthesis","volume-title":"Proceedings of the 35th International Conference on Machine Learning, ICML","volume":"80","author":"Kalchbrenner"},{"key":"ref24","article-title":"Mongolian text-to-speech challenge under low-resource scenario"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683682"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.919072"}],"event":{"name":"2024 27th International Conference on Computer Supported Cooperative Work in Design (CSCWD)","start":{"date-parts":[[2024,5,8]]},"location":"Tianjin, China","end":{"date-parts":[[2024,5,10]]}},"container-title":["2024 27th International Conference on Computer Supported Cooperative Work in Design (CSCWD)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10579968\/10579982\/10580278.pdf?arnumber=10580278","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,18]],"date-time":"2024-07-18T05:02:54Z","timestamp":1721278974000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10580278\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,8]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/cscwd61410.2024.10580278","relation":{},"subject":[],"published":{"date-parts":[[2024,5,8]]}}}