{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T23:41:25Z","timestamp":1725579685992},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"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":[[2021,12,13]]},"DOI":"10.1109\/asru51503.2021.9688058","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T20:31:00Z","timestamp":1643920260000},"page":"62-67","source":"Crossref","is-referenced-by-count":0,"title":["Latency-Controlled Neural Architecture Search for Streaming Speech Recognition"],"prefix":"10.1109","author":[{"given":"Liqiang","family":"He","sequence":"first","affiliation":[{"name":"Tencent AI Lab,Shenzhen,China"}]},{"given":"Shulin","family":"Feng","sequence":"additional","affiliation":[{"name":"Tencent AI Lab,Shenzhen,China"}]},{"given":"Dan","family":"Su","sequence":"additional","affiliation":[{"name":"Tencent AI Lab,Shenzhen,China"}]},{"given":"Dong","family":"Yu","sequence":"additional","affiliation":[{"name":"Tencent AI Lab,Bellevue,WA,USA"}]}],"member":"263","reference":[{"key":"ref10","first-page":"11217","article-title":"Aows: Adaptive and optimal network width search with latency constraints","author":"maxim","year":"0","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3028288"},{"key":"ref12","article-title":"Darts: Differentiable architecture search","author":"liu","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00138"},{"key":"ref14","article-title":"Weight-sharing neural architecture search: A battle to shrink the optimization gap","author":"xie","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref16","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref17","first-page":"1747","article-title":"Pixel recurrent neural networks","author":"van oord","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref19","article-title":"Aishell-2: transforming mandarin asr research into industrial scale","author":"du","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1315"},{"key":"ref3","first-page":"6788","article-title":"Learned transferable ar-chitectures can surpass hand-designed architectures for large scale speech recognition","author":"he","year":"0","journal-title":"ICASSP 2021 — 2021 IEEE Inter-national Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1258"},{"key":"ref5","article-title":"Autokws: Keyword spot-ting with differentiable architecture search","author":"zhang","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref8","article-title":"Latency-aware differentiable neural architecture search","author":"xu","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414403"},{"key":"ref2","article-title":"Neural architecture search for speech recognition","author":"hu","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref9","article-title":"Lc-nas: Latency constrained neural ar-chitecture search for point cloud networks","author":"li","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref1","article-title":"Neural architecture search on acoustic scene classification","author":"li","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053568"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472805"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref24","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and man-darin","author":"amodei","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178838"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413535"},{"key":"ref25","first-page":"2132","article-title":"Streaming Transformer-Based Acous-tic Models Using Self-Attention with Augmented Memory","author":"wu","year":"0","journal-title":"Proc Interspeech 2020"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2021,12,13]]},"location":"Cartagena, Colombia","end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9687821\/9687855\/09688058.pdf?arnumber=9688058","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T20:42:22Z","timestamp":1652733742000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9688058\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9688058","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}