乐胖代购免代理版

{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,7]],"date-time":"2024-07-07T06:41:06Z","timestamp":1720334466291},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62301521","U23B2053"],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003995","name":"Natural Science Foundation of Anhui Province","doi-asserted-by":"publisher","award":["2308085QF200"],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["WK2100000033"],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3417347","type":"journal-article","created":{"date-parts":[[2024,6,20]],"date-time":"2024-06-20T17:46:13Z","timestamp":1718905573000},"page":"3256-3269","source":"Crossref","is-referenced-by-count":0,"title":["APCodec: A Neural Audio Codec With Parallel Amplitude and Phase Spectrum Encoding and Decoding"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"http:\/\/orcid.org\/0000-0001-6668-022X","authenticated-orcid":false,"given":"Yang","family":"Ai","sequence":"first","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"}]},{"given":"Xiao-Hang","family":"Jiang","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"http:\/\/orcid.org\/0009-0009-8026-0702","authenticated-orcid":false,"given":"Ye-Xin","family":"Lu","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"}]},{"given":"Hui-Peng","family":"Du","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"http:\/\/orcid.org\/0000-0001-7853-5273","authenticated-orcid":false,"given":"Zhen-Hua","family":"Ling","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"}]}],"member":"263","reference":[{"issue":"10","key":"ref1","first-page":"780","article-title":"ISO\/MPEG-1 audio: A generic standard for coding of high-quality digital audio","volume":"42","author":"Brandenburg","year":"1994","journal-title":"J. Audio Eng. Soc."},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1976.1170021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1986.1164946"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/25.312763"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref6","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"},{"key":"ref7","article-title":"SpeechTokenizer: Unified speech tokenizer for speech large language models","author":"Zhang","year":"2023"},{"key":"ref8","article-title":"RepCodec: A speech representation codec for speech tokenization","author":"Huang","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448454"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/45.1890"},{"key":"ref11","article-title":"High-quality, low-delay music coding in the opus codec","volume":"135","author":"Valin","year":"2013","journal-title":"Audio Eng. Soc. Conv."},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179063"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462529"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682435"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1255"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632750"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1562"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096056"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096243"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/T-AIEE.1947.5059525"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461487"},{"key":"ref22","article-title":"Neural discrete representation learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Van Den Oord","year":"2017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683277"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1816"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref26","article-title":"High fidelity neural audio compression","author":"Dfossez","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MP.2006.1664069"},{"key":"ref28","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kong","year":"2020"},{"key":"ref29","article-title":"HiFi-Codec: Group-residual vector quantization for high fidelity audio codec","author":"Yang","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-537"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095442"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1490"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096509"},{"key":"ref34","article-title":"High-fidelity audio compression with improved rvqgan","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar","year":"2023"},{"key":"ref35","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"ref37","article-title":"Gaussian error linear units (gelus","author":"Hendrycks","year":"2016"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096553"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3277276"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1016"},{"key":"ref41","article-title":"Rectifier nonlinearities improve neural network acoustic models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Maas","year":"2013"},{"key":"ref42","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Kumar","year":"2019"},{"key":"ref43","article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92)","author":"Yamagishi","year":"2019"},{"key":"ref44","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2018"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX48832.2020.9123150"},{"key":"ref47","article-title":"Towards high-quality and efficient speech bandwidth extension with parallel amplitude and phase prediction","author":"Lu","year":"2024"},{"key":"ref48","volume-title":"Method for the Subjective Assessment of Intermediate Sound Quality (MUSHRA)","year":"2001"},{"key":"ref49","first-page":"4218","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proc. Int. Conf. Computat. Linguistics, Lang. Resour.","author":"Ardila","year":"2020"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-48"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570655\/10304349\/10565949.pdf?arnumber=10565949","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,7]],"date-time":"2024-07-07T05:34:02Z","timestamp":1720330442000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10565949\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3417347","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}