{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T17:21:35Z","timestamp":1778692895148,"version":"3.51.4"},"reference-count":23,"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\/icassp49357.2023.10095105","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":16,"title":["DSPGAN: A Gan-Based Universal Vocoder for High-Fidelity TTS by Time-Frequency Domain Supervision from DSP"],"prefix":"10.1109","author":[{"given":"Kun","family":"Song","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongmao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Lei","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Cong","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanzhao","family":"Li","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"He","sequence":"additional","affiliation":[{"name":"TAL Education Group,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinfeng","family":"Bai","sequence":"additional","affiliation":[{"name":"TAL Education Group,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-68"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682298"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-349"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383551"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746709"},{"key":"ref21","article-title":"Delightfultts: The microsoft speech synthesis system for blizzard challenge 2021","author":"liu","year":"2021","journal-title":"CoRR"},{"key":"ref2","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","author":"kim","year":"2021","journal-title":"Proceedings of the 38th International Conference on Machine Learning ICML 2021"},{"key":"ref1","article-title":"End-to-end adversarial text-to-speech","author":"donahue","year":"2021","journal-title":"9th International Conference on Learning Representations ICLR 2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3188"},{"key":"ref16","article-title":"DDSP: differentiable digital signal processing","author":"engel","year":"0"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-755"},{"key":"ref18","article-title":"Superseded-cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit","author":"veaux","year":"2017"},{"key":"ref8","article-title":"Diffwave: A versatile diffusion model for audio synthesis","author":"kong","year":"2021"},{"key":"ref7","first-page":"7706","article-title":"Wave-flow: A compact flow-based model for raw audio","author":"ping","year":"0","journal-title":"Proceedings of the 37th International Conference on Machine Learning ICML 2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.564"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref3","first-page":"14881","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","author":"kumar","year":"2019","journal-title":"Advances in Neural Information Processing Systems 32 Annual Conference on Neural Information Processing Systems 2019 NeurIPS 2019"},{"key":"ref6","first-page":"3617","article-title":"Waveg-low: A flow-based generative network for speech synthesis","author":"prenger","year":"2019","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing ICASSP 2019"},{"key":"ref5","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"2020","journal-title":"Advances in Neural Information Processing Systems 33 Annual Conference on Neural Information Processing Systems 2020 NeurIPS 2020"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"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\/10095105.pdf?arnumber=10095105","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:01:30Z","timestamp":1700506890000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095105\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095105","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}