{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T10:08:53Z","timestamp":1764842933238,"version":"3.37.3"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,2,15]],"date-time":"2025-02-15T00:00:00Z","timestamp":1739577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,2,15]],"date-time":"2025-02-15T00:00:00Z","timestamp":1739577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,15]],"date-time":"2025-02-15T00:00:00Z","timestamp":1739577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2024A1515010112"],"award-info":[{"award-number":["2024A1515010112"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006639","name":"Changsha Natural Science Foundation","doi-asserted-by":"publisher","award":["kq2402082"],"award-info":[{"award-number":["kq2402082"]}],"id":[{"id":"10.13039\/100006639","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2025,2,15]]},"DOI":"10.1109\/jiot.2024.3483232","type":"journal-article","created":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T17:32:34Z","timestamp":1729272754000},"page":"4169-4182","source":"Crossref","is-referenced-by-count":7,"title":["Reparameterization of Lightweight Transformer for On-Device Speech Emotion Recognition"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8487-0561","authenticated-orcid":false,"given":"Zixing","family":"Zhang","sequence":"first","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8074-1746","authenticated-orcid":false,"given":"Zhongren","family":"Dong","sequence":"additional","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weixiang","family":"Xu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5776-6849","authenticated-orcid":false,"given":"Jing","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, University of Cambridge, Cambridge, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3102471"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3039359"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3486618"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2023.3254668"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2021.3056421"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/BigData47090.2019.9005638"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/s23062948"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2772959"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11431-020-1647-3"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3505244"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263585"},{"key":"ref13","article-title":"A survey of large language models","author":"Zhao","year":"2023","journal-title":"arXiv:2303.18223"},{"key":"ref14","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. 34th Annu. Conf. Neural Inf. Process. Syst. (NeuIPS)","author":"Brown"},{"key":"ref15","article-title":"PanGu-\u03c3: Towards trillion parameter language model with sparse heterogeneous computing","author":"Ren","year":"2023","journal-title":"arXiv:2303.10845"},{"key":"ref16","article-title":"Training compute-optimal large language models","author":"Hoffmann","year":"2022","journal-title":"arXiv:2203.15556"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.2976475"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975749"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2022.3226481"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3154605"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00413"},{"issue":"6","key":"ref22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3530811","article-title":"Efficient transformers: A survey","volume":"55","author":"Tay","year":"2022","journal-title":"ACM Comput. Surv."},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-281"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09276-9"},{"key":"ref25","article-title":"Linformer: Self-attention with linear complexity","author":"Wang","year":"2020","journal-title":"arXiv:2006.04768"},{"key":"ref26","article-title":"WakeUpNet: A mobile-transformer based framework for end-to-end streaming voice trigger","author":"Zhang","year":"2022","journal-title":"arXiv:2210.02904"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123383"},{"key":"ref28","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020","journal-title":"arXiv:2001.08361"},{"key":"ref29","article-title":"Scaling laws for autoregressive generative modeling","author":"Henighan","year":"2020","journal-title":"arXiv:2010.14701"},{"key":"ref30","first-page":"3331","article-title":"The power of interpolation: Understanding the effectiveness of SGD in modern over-parametrized learning","volume-title":"Proc. 35th Int. Conf. Mach. Learn. (ICML)","author":"Ma"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054073"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-56"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2822"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-74"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094651"},{"key":"ref36","article-title":"A fine-tuned wav2vec 2.0\/HuBERT benchmark for speech emotion recognition, speaker verification and spoken language understanding","author":"Wang","year":"2021","journal-title":"arXiv:2111.02735"},{"key":"ref37","first-page":"14014","article-title":"Are sixteen heads really better than one?","volume-title":"Proc. 33th Annu. Conf. Neural Inf. Process. Syst. (NeuIPS)","author":"Michel"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1580"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.259"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.171"},{"key":"ref41","article-title":"Reducing transformer depth on demand with structured dropout","author":"Fan","year":"2019","journal-title":"arXiv:1909.11556"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2022.101429"},{"key":"ref43","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019","journal-title":"arXiv:1910.01108"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.195"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747490"},{"key":"ref47","first-page":"29449","article-title":"FMMformer: Efficient and flexible transformer via decomposed near-field and far-field attention","volume-title":"Proc. 35th Annu. Conf. Neural Inf. Process. Syst. (NeuIPS)","author":"Nguyen"},{"key":"ref48","first-page":"1","article-title":"Is attention better than matrix decomposition?","volume-title":"Proc. 9th Int. Conf. Learn. Represent. (ICLR)","author":"Geng"},{"key":"ref49","first-page":"29321","article-title":"DRONE: Data-aware low-rank compression for large NLP models","volume-title":"Proc. 34th Annu. Conf. Neural Inf. Process. Syst. (NeuIPS)","author":"Chen"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053878"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3166790"},{"key":"ref52","first-page":"1298","article-title":"ExpandNets: Linear over-parameterization to train compact convolutional networks","volume-title":"Proc. 34th Annu. Conf. Neural Inf. Process. Syst. (NeuIPS)","author":"Guo"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00200"},{"key":"ref55","article-title":"Transformer-transducer: End-to-end speech recognition with self-attention","author":"Yeh","year":"2019","journal-title":"arXiv:1910.12977"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref57","first-page":"244","article-title":"On the optimization of deep networks: Implicit acceleration by overparameterization","volume-title":"Proc. 35th Int. Conf. Mach. Learn. (ICML)","author":"Arora"},{"key":"ref58","article-title":"Scaling laws for transfer","author":"Hernandez","year":"2021","journal-title":"arXiv:2102.01293"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.391"},{"key":"ref61","first-page":"3123","article-title":"The distress analysis interview corpus of human and computer interviews","volume-title":"Proc. 9th Int. Conf. Lang. Resour. Eval. (LREC)","author":"Gratch"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2022.3161411"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3117062"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3247822"},{"key":"ref65","first-page":"6155","article-title":"Learning and Generalization in Overparameterized neural networks","volume-title":"Proc. 33th Annu. Conf. Neural Inf. Process. Syst. (NeuIPS)","author":"Allen-Zhu"},{"key":"ref66","first-page":"242","article-title":"A convergence theory for deep learning via over-parameterization","volume-title":"Proc. 36th Int. Conf. Mach. Learn. (ICML)","author":"Allen-Zhu"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414006"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054323"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68790-8_1"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/IC_ASET49463.2020.9318302"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ElConRus51938.2021.9396540"},{"key":"ref72","first-page":"2280","article-title":"Double trouble in double descent: Bias and variance(s) in the lazy regime","volume-title":"Proc. 37th Int. Conf. Mach. Learn. (ICML)","author":"d\u2019Ascoli"},{"key":"ref73","first-page":"1","article-title":"Deep double descent: Where bigger models and more data hurt","volume-title":"Proc. 8th Int. Conf. Learn. Represent. (ICLR)","author":"Nakkiran"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488907\/10874850\/10722866.pdf?arnumber=10722866","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T18:48:30Z","timestamp":1738867710000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10722866\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,15]]},"references-count":73,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2024.3483232","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"type":"electronic","value":"2327-4662"},{"type":"electronic","value":"2372-2541"}],"subject":[],"published":{"date-parts":[[2025,2,15]]}}}