{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T05:16:25Z","timestamp":1778649385598,"version":"3.51.4"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"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":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434736","type":"proceedings-article","created":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T19:46:15Z","timestamp":1778615175000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["A Universal Harmonic Discriminator for High-quality GAN-based Vocoder"],"prefix":"10.1109","author":[{"given":"Nan","family":"Xu","sequence":"first","affiliation":[{"name":"HUJING Digital Media & Entertainment Group,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaolong","family":"Huang","sequence":"additional","affiliation":[{"name":"HUJING Digital Media & Entertainment Group,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Zeng","sequence":"additional","affiliation":[{"name":"HUJING Digital Media & Entertainment Group,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.235"},{"key":"ref2","first-page":"3171","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume":"32","author":"Ren","year":"2019","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref3","first-page":"1399","article-title":"A3t: Alignment-aware acoustic and text pretraining for speech synthesis and editing","volume-title":"International Conference on Machine Learning (ICML)","author":"Bai"},{"key":"ref4","article-title":"Mega-tts 2: Boosting prompting mechanisms for zero-shot speech synthesis","volume-title":"International Conference on Learning Representations (ICLR)","author":"Jiang"},{"key":"ref5","first-page":"13916","article-title":"Make-an-audio: Text-to-audio generation with prompt-enhanced diffusion models","volume-title":"International Conference on Machine Learning (ICML)","author":"Huang"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399607"},{"key":"ref7","article-title":"Periodwave: Multi-period flow matching for high-fidelity waveform generation","volume-title":"International Conference on Learning Representations (ICLR)","author":"Sang-Hoon"},{"key":"ref8","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","volume":"33","author":"Kong","year":"2020"},{"key":"ref9","article-title":"Bigvgan: A universal neural vocoder with large-scale training","volume-title":"International Conference on Learning Representations (ICLR)","author":"Lee"},{"key":"ref10","first-page":"14910","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","volume":"32","author":"Kumar","year":"2019"},{"key":"ref11","article-title":"Tfgan: Time and frequency domain based generative adversarial network for high-fidelity speech synthesis","author":"Tian","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-583"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1016"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095105"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00293"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26479"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2970241"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746713"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1726"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3277276"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-0601-3_6"},{"key":"ref22","article-title":"Vocos: Closing the gap between time-domain and fourier-based neural vocoders for high-quality audio synthesis","volume-title":"International Conference on Learning Representations (ICLR)","author":"Siuzdak"},{"key":"ref23","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2023","journal-title":"Transactions on Machine Learning Research (TMLR)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/78.258122"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1121\/1.404385"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448436"},{"key":"ref27","first-page":"3","article-title":"Constant-q transform toolbox for music processing","author":"Sch\u00f6rkhuber","year":"2010","journal-title":"Sound and Music Computing"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053038"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053669"},{"issue":"1\/2","key":"ref30","first-page":"52","article-title":"Modified discrete cosine transform: Its implications for audio coding and error concealment","volume":"51","author":"Wang","year":"2003","journal-title":"Journal of the Audio Engineering Society (AES)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445878"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/0378-5955(90)90170-T"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1584"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475437"},{"key":"ref35","first-page":"271","article-title":"Cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit (version 0.92)","author":"Yamagishi","year":"2019","journal-title":"University of Edinburgh. The Centre for Speech Technology Research (CSTR)"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0501"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-48"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434736.pdf?arnumber=11434736","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T04:59:03Z","timestamp":1778648343000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434736\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434736","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}