{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:05:57Z","timestamp":1740099957041,"version":"3.37.3"},"reference-count":33,"publisher":"IEEE","funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,19]]},"DOI":"10.1109\/slt48900.2021.9383532","type":"proceedings-article","created":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T20:46:54Z","timestamp":1616705214000},"page":"82-88","source":"Crossref","is-referenced-by-count":6,"title":["Multi-Quartznet: Multi-Resolution Convolution for Speech Recognition with Multi-Layer Feature Fusion"],"prefix":"10.1109","author":[{"given":"Jian","family":"Luo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianzong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ning","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guilin","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Multi-head monotonic chunkwise attention for online speech recognition","year":"2020","author":"liu","key":"ref33"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2933146"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"article-title":"Xceptiontime: A novel deep architecture based on depthwise separable convolutions for hand gesture classification","year":"2019","author":"rahimian","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1973"},{"article-title":"Multi-stream end-to-end speech recognition","year":"2019","author":"li","key":"ref12"},{"article-title":"Multi-encoder multi-resolution framework for end-to-end speech recognition","year":"2018","author":"li","key":"ref13"},{"article-title":"Multi-scale octave convolutions for robust speech recognition","year":"2019","author":"rownicka","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003730"},{"article-title":"Squeeze-and-excitation networks","year":"2017","author":"hu","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"article-title":"Densely connected convolutional networks","year":"2016","author":"huang","key":"ref18"},{"article-title":"Feature pyra-mid networks for object detection","year":"2016","author":"lin","key":"ref19"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054260"},{"key":"ref4","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","author":"amodei","year":"2015","journal-title":"Computer Science"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2203"},{"key":"ref3","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"hannun","year":"2014","journal-title":"Computer Science"},{"article-title":"Fully convolutional speech recognition","year":"2018","author":"zeghidour","key":"ref6"},{"key":"ref29","article-title":"Combiner: Inductively learning tree structured attention in transformer","author":"wu","year":"2020","journal-title":"ICLRE"},{"key":"ref5","article-title":"Wav2letter: an end-to-end convnet-based speech recognition system","author":"collobert","year":"2016","journal-title":"Computer Science"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2460"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1819"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178838"},{"key":"ref9","article-title":"Depthwise-stft based separable convolutional neural net-works","author":"kumawat","year":"2020","journal-title":"ICASSP"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053889"},{"article-title":"Augfpn: Improving multi-scale fea-ture learning for object detection","year":"2019","author":"guo","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1089"},{"article-title":"Cross-layer feature pyramid net-work for salient object detection","year":"2020","author":"li","key":"ref21"},{"article-title":"Stochastic gradient methods with layer-wise adaptive moments for training of deep networks","year":"2019","author":"ginsburg","key":"ref24"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682490"},{"article-title":"Sgdr: Stochastic gradient descent with warm restarts","year":"2016","author":"loshchilov","key":"ref25"}],"event":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2021,1,19]]},"location":"Shenzhen, China","end":{"date-parts":[[2021,1,22]]}},"container-title":["2021 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9383468\/9383452\/09383532.pdf?arnumber=9383532","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,31]],"date-time":"2021-05-31T21:30:45Z","timestamp":1622496645000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9383532\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,19]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/slt48900.2021.9383532","relation":{},"subject":[],"published":{"date-parts":[[2021,1,19]]}}}