{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T07:40:06Z","timestamp":1735026006511,"version":"3.32.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"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":[[2024,11,7]]},"DOI":"10.1109\/iscslp63861.2024.10800135","type":"proceedings-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:11:17Z","timestamp":1734981077000},"page":"71-75","source":"Crossref","is-referenced-by-count":0,"title":["A Differential Quantization Based End-to-End Neural Speech Codec"],"prefix":"10.1109","author":[{"given":"Pincheng","family":"Lu","sequence":"first","affiliation":[{"name":"School of Information and Electronics, Beijing Institute of Technology,Beijing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Information and Electronics, Beijing Institute of Technology,Beijing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information and Electronics, Beijing Institute of Technology,Beijing"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Definition of the opus audio codec","author":"Valin","year":"2012","journal-title":"Internet Engineering Task Force (IETF), RFC 6716"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179063"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1121\/1.1912679"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1985.1168147"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref7","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Hifi-codec: Group-residual vector quantization for high fidelity audio codec","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref11","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095442"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref15","article-title":"Seanet: A multimodal speech enhancement network","author":"Tagliasacchi","year":"2020","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447532"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref18","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-755"},{"key":"ref21","first-page":"1534","article-title":"Method for the subjective assessment of intermediate quality level of coding systems","volume-title":"ITU-R BS","author":"Recommendation","year":"2003"},{"key":"ref22","first-page":"1","article-title":"Visqol: The virtual speech quality objective listener","volume-title":"IWAENC 2012; international workshop on acoustic signal enhancement","author":"Hines","year":"2012"}],"event":{"name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2024,11,7]]},"location":"Beijing, China","end":{"date-parts":[[2024,11,10]]}},"container-title":["2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10799944\/10799969\/10800135.pdf?arnumber=10800135","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T06:33:06Z","timestamp":1735021986000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10800135\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/iscslp63861.2024.10800135","relation":{},"subject":[],"published":{"date-parts":[[2024,11,7]]}}}