{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:41:40Z","timestamp":1730266900581,"version":"3.28.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10651390","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Generative Spoken Language Modeling with Quantized Feature Enhancement"],"prefix":"10.1109","author":[{"given":"Feiyu","family":"Duan","sequence":"first","affiliation":[{"name":"Beihang University,Sino-French Engineer School,China"}]},{"given":"Chen","family":"Li","sequence":"additional","affiliation":[{"name":"Beihang University,School of Computer Science and Engineering,China"}]},{"given":"Keheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Beihang University,Sino-French Engineer School,China"}]},{"given":"Si","family":"Wu","sequence":"additional","affiliation":[{"name":"Orange R&D Beijing Company Limited,Beijing,China"}]},{"given":"Chuantao","family":"Yin","sequence":"additional","affiliation":[{"name":"Beihang University,Sino-French Engineer School,China"}]},{"given":"Wenge","family":"Rong","sequence":"additional","affiliation":[{"name":"Beihang University,School of Computer Science and Engineering,China"}]}],"member":"263","reference":[{"article-title":"Language models are few-shot learners","volume-title":"Proceedings of 34th Annual Conference on Neural Information Processing Systems","author":"Brown","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref4","first-page":"5504","article-title":"Mu2slam: Multitask, multilingual speech and language models","volume-title":"Proceedings of 40th International Conference on Machine Learning","volume":"202","author":"Cheng"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1055"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.593"},{"key":"ref7","first-page":"1336","article-title":"On generative spoken language modeling from raw audio","volume":"9","author":"Lakhotia","year":"2021","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01755"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3145297"},{"key":"ref10","first-page":"18 003","article-title":"ContentVec: An improved self-supervised speech representation by disentangling speakers","volume-title":"Proceedings of 39th International Conference on Machine Learning","author":"Qian"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.63"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-749"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-817"},{"key":"ref14","first-page":"6306","article-title":"Neural discrete representation learning","volume-title":"Proceedings of 31st Annual Conference on Neural Information Processing Systems","author":"van den Oord"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1959.1104847"},{"article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proceedings of 34th Annual Conference on Neural Information Processing Systems","author":"Baevski","key":"ref16"},{"key":"ref17","article-title":"Jukebox: A generative model for music","volume":"abs\/2005.00341","author":"Dhariwal","year":"2020","journal-title":"CoRR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-438"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383461"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.31234\/osf.io\/rx94d","article-title":"Can statistical learning bootstrap early language acquisition? a modeling investigation","author":"Lavechin","year":"2022"},{"key":"ref23","article-title":"Representation learning with contrastive predictive coding","volume":"abs\/1807.03748","author":"van den Oord","year":"2018","journal-title":"CoRR"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref28","article-title":"SpeechGen: Unlocking the generative power of speech language models with prompts","volume":"abs\/2306.02207","author":"Wu","year":"2023","journal-title":"CoRR"},{"key":"ref29","article-title":"Neural codec language models are zero-shot text to speech synthesizers","volume":"abs\/2301.02111","author":"Wang","year":"2023","journal-title":"CoRR"},{"key":"ref30","first-page":"3331","article-title":"CHiVE: Varying prosody in speech synthesis with a linguistically driven dynamic hierarchical conditional variational network","volume-title":"Proceedings of the 36th International Conference on Machine Learning","author":"Kenter"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053520"},{"key":"ref32","first-page":"5167","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"Proceedings of the 35th International Conference on Machine Learning","author":"Wang"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2096"},{"key":"ref34","first-page":"11 134","article-title":"Learning de-identified representations of prosody from raw audio","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Weston"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2024,6,30]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10651390.pdf?arnumber=10651390","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T06:38:11Z","timestamp":1725950291000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10651390\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10651390","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}