{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T05:13:54Z","timestamp":1735103634863,"version":"3.32.0"},"reference-count":26,"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"}],"funder":[{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L233032,L223033"],"award-info":[{"award-number":["L233032,L223033"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62471012"],"award-info":[{"award-number":["62471012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,11,7]]},"DOI":"10.1109\/iscslp63861.2024.10800201","type":"proceedings-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:11:17Z","timestamp":1734981077000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["A Hybrid DFSMN and Mamba Architecture for Low Bitrate Neural Speech Coding"],"prefix":"10.1109","author":[{"given":"Yuhao","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, Beijing University of Technology,Beijing"}]},{"given":"Maoshen","family":"Jia","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Beijing University of Technology,Beijing"}]},{"given":"Jiawei","family":"Ru","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Beijing University of Technology,Beijing"}]},{"given":"Junqi","family":"Tai","sequence":"additional","affiliation":[{"name":"Beijing-Dublin International College, Beijing University of Technology,Beijing"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1985.1168147"},{"key":"ref2","article-title":"Review of the Opus codec in a WebRTc scenario for audio and speech communication","volume-title":"Speech and Computer: 17th International Conference, SPECOM 2015","author":"Michael","year":"2015"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462529"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682435"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415120"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref7","first-page":"arXiv.org, 2022\u201310","article-title":"High Fidelity Neural Audio Compression","author":"D\u00e9fossez","year":"2022","journal-title":"arXiv.Org"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096509"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746296"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095442"},{"key":"ref11","first-page":"arXiv.org, 2023\u201305","article-title":"HiFi-Codec: Group-Residual Vector Quantization for High Fidelity Audio Codec","author":"Dongchao","year":"2023","journal-title":"arXiv.Org"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref15","first-page":"arXiv.org, 2016\u201303","article-title":"Quantifying the Vanishing Gradient and Long Distance Dependency Problem in Recursive Neural Networks and Recursive LSTMs","author":"Phong","year":"2016","journal-title":"arXiv.Org"},{"key":"ref16","first-page":"arXiv.org, 2022\u201308","article-title":"Efficiently Modeling Long Sequences with Structured State Spaces","author":"Albert","year":"2022","journal-title":"arXiv.Org"},{"key":"ref17","first-page":"arXiv.org, 2023\u201312","article-title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","author":"Albert","year":"2023","journal-title":"arXiv.Org"},{"key":"ref18","first-page":"arXiv.org, 2024\u201302","article-title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","author":"Lianghui","year":"2024","journal-title":"arXiv.Org"},{"key":"ref19","first-page":"arXiv.org, 2016\u201301","article-title":"Feedforward Sequential Memory Networks: A New Structure to Learn Long-Term Dependency","author":"Shiliang","year":"2016","journal-title":"arXiv.Org"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461404"},{"key":"ref21","first-page":"arXiv.org, 2024\u201304","article-title":"SPMamba: State-Space Model Is All You Need in Speech Separation","author":"Kai","year":"2024","journal-title":"arXiv.Org"},{"key":"ref22","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Jungil","year":"2020","journal-title":"Advances in neural information processing systems"},{"issue":"1","key":"ref23","doi-asserted-by":"crossref","first-page":"014802","DOI":"10.1121\/10.0003321","article-title":"On the Importance of Power Compression and Phase Estimation in Monaural Speech Dereverberation","volume":"1","author":"Andong","year":"2021","journal-title":"JASA Express Letters"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"volume-title":"Noisy speech database for training speech enhancement algorithms and tts models","year":"2017","author":"Valentini-Botinhao","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX48832.2020.9123150"}],"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\/10800201.pdf?arnumber=10800201","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T06:26:14Z","timestamp":1735021574000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10800201\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/iscslp63861.2024.10800201","relation":{},"subject":[],"published":{"date-parts":[[2024,11,7]]}}}