{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T01:59:29Z","timestamp":1772935169843,"version":"3.50.1"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"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":[[2025,12,8]]},"DOI":"10.1109\/bigdata66926.2025.11400898","type":"proceedings-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:57:57Z","timestamp":1772830677000},"page":"221-228","source":"Crossref","is-referenced-by-count":0,"title":["Edge-Optimized Voice Control with 0.26 M Parameters: Distilling 86M Adaptive Window Audio Transformer for Real-World Variable-Length Inputs"],"prefix":"10.1109","author":[{"given":"Pinze","family":"Ren","sequence":"first","affiliation":[{"name":"Tsinghua University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen","family":"Chen","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinjun","family":"Wu","sequence":"additional","affiliation":[{"name":"Peking University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiran","family":"Lin","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qilong","family":"Shi","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianxin","family":"Yang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/s20247287"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107807"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/jiot.2016.2579198"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2024.107938"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3328283"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3626641.3626946"},{"key":"ref7","volume-title":"AST: Audio Spectrogram Transformer","author":"Gong"},{"key":"ref8","article-title":"EAT: SelfSupervised Pre-Training with Efficient Audio Transformer","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-249"},{"key":"ref10","article-title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","author":"Sandler","year":"2019","journal-title":"arXiv preprint arXiv"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178838"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref15","article-title":"Sequence to sequence learning with neural networks","author":"Sutskever","journal-title":"NIPS2014"},{"key":"ref16","article-title":"An Image is Worth 16 \u00d7 16 Words: Transformers for Image Recognition at Scale","volume-title":"arXiv preprint arXiv","author":"Dosovitskiy"},{"key":"ref17","article-title":"How to train your ViT?","volume-title":"Data, Augmentation, and Regularization in Vision Transformers","author":"Steiner"},{"key":"ref18","volume-title":"When Vision Transformers Outperform ResNets without Pretraining or Strong Data Augmentations","author":"Chen"},{"key":"ref19","volume-title":"MLP-Mixer: An all-MLP Architecture for Vision","author":"Tolstikhin"},{"key":"ref20","first-page":"10347","article-title":"Training data-efficient image transformers and distillation through attention","volume-title":"International Conference on Machine Learning","author":"Touvron","year":"2021"},{"key":"ref21","volume-title":"Speech Commands: A Dataset for LimitedVocabulary Speech Recognition","author":"Warden","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3644853"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-0791-1_16"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref25","volume-title":"ImageNet-21K Pretraining for the Masses","author":"Ridnik","year":"2021"},{"key":"ref26","volume-title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","author":"Sandler","year":"2019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"ref28","volume-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","author":"Simonyan","year":"2015"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52688.2022.01167","volume-title":"A ConvNet for the 2020s","author":"Liu","year":"2022"},{"key":"ref30","first-page":"740","article-title":"Electron spectroscopy studies on magneto-optical media and plastic substrate interface","volume-title":"google\/vit-base-patch16-224","volume":"2","author":"Yorozu","year":"1987"}],"event":{"name":"2025 IEEE International Conference on Big Data (BigData)","location":"Macau, China","start":{"date-parts":[[2025,12,8]]},"end":{"date-parts":[[2025,12,11]]}},"container-title":["2025 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11400704\/11400712\/11400898.pdf?arnumber=11400898","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T07:25:50Z","timestamp":1772868350000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11400898\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/bigdata66926.2025.11400898","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]}}}