{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T21:04:48Z","timestamp":1750799088998,"version":"3.37.3"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,13]],"date-time":"2022-10-13T00:00:00Z","timestamp":1665619200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,13]],"date-time":"2022-10-13T00:00:00Z","timestamp":1665619200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,10,13]]},"DOI":"10.1109\/dsaa54385.2022.10032360","type":"proceedings-article","created":{"date-parts":[[2023,2,8]],"date-time":"2023-02-08T18:54:03Z","timestamp":1675882443000},"page":"1-8","source":"Crossref","is-referenced-by-count":3,"title":["Adaptive Sparse and Monotonic Attention for Transformer-based Automatic Speech Recognition"],"prefix":"10.1109","author":[{"given":"Chendong","family":"Zhao","sequence":"first","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianzong","family":"Wang","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenqi","family":"Wei","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyang","family":"Qu","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoqian","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University,The Shenzhen International Graduate School,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Xiao","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2203"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1938"},{"key":"ref4","first-page":"577","article-title":"Attention-based models for speech recognition","volume":"28","author":"Chorowski","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2016.7472621"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414694"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414103"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746051"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383517"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2039"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892604"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892002"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534208"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2022.3187103"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01698"},{"article-title":"Learning to generate realistic noisy images via pixel-level noise-aware adversarial training","volume-title":"Thirty-Fifth Conference on Neural Information Processing Systems","author":"Cai","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_41"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413429"},{"key":"ref19","first-page":"1614","article-title":"From softmax to sparsemax: A sparse model of attention and multi-label classification","volume-title":"International Conference on Machine Learning","author":"Martins"},{"key":"ref20","first-page":"3338","article-title":"A regularized framework for sparse and structured neural attention","author":"Niculae","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1223"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414694"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054245"},{"article-title":"Sparsemap: Differentiable sparse structured inference","volume-title":"International Conference on Machine Learning","author":"Niculae","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2059"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5444"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/0375-9601(93)90195-6"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1146"},{"key":"ref29","first-page":"2837","article-title":"Online and linear-time attention by enforcing monotonic alignments","volume-title":"International Conference on Machine Learning","author":"Raffel"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683602"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004027"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1938"},{"article-title":"Monotonic chunkwise attention","volume-title":"International Conference on Learning Representations (ICLR)","author":"Chiu","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2218"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1126"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"article-title":"Monotonic multihead attention","volume-title":"International Conference on Learning Representations (ICLR)","author":"Ma","key":"ref38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1780"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2112"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683510"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682954"},{"key":"ref44","first-page":"606","article-title":"Learning classifiers with fenchel-young losses: Generalized entropies, margins, and algorithms","volume-title":"The 22nd International Conference on Artificial Intelligence and Statistics","author":"Blondel"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref46","article-title":"Fully convolutional speech recognition","author":"et al","year":"2018","journal-title":"CoRR"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1819"},{"article-title":"Explicit sparse transformer: Concentrated attention through explicit selection","year":"2019","author":"Guangxiang Zhao","key":"ref48"},{"article-title":"Generating long sequences with sparse transformers","volume-title":"Annual Conference of the North American Chapter of the Association for Computational Linguistics","author":"Child","key":"ref49"},{"article-title":"Combiner: Inductively learning tree structured attention in transformer","volume-title":"International Conference on Learning Representations","author":"Wu","key":"ref50"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054260"}],"event":{"name":"2022 IEEE 9th International Conference on Data Science and Advanced Analytics (DSAA)","start":{"date-parts":[[2022,10,13]]},"location":"Shenzhen, China","end":{"date-parts":[[2022,10,16]]}},"container-title":["2022 IEEE 9th International Conference on Data Science and Advanced Analytics (DSAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10032305\/10032324\/10032360.pdf?arnumber=10032360","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T09:55:40Z","timestamp":1707818140000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10032360\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,13]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/dsaa54385.2022.10032360","relation":{},"subject":[],"published":{"date-parts":[[2022,10,13]]}}}