{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T10:15:47Z","timestamp":1752228947968,"version":"3.37.3"},"reference-count":37,"publisher":"IEEE","funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008343","name":"Beijing Language and Culture University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008343","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,24]]},"DOI":"10.1109\/iscslp49672.2021.9362063","type":"proceedings-article","created":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T23:37:05Z","timestamp":1614641825000},"page":"1-5","source":"Crossref","is-referenced-by-count":6,"title":["Multi-Scale Model for Mandarin Tone Recognition"],"prefix":"10.1109","author":[{"given":"Linkai","family":"Peng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wang","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dengfeng","family":"Ke","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinsong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","first-page":"91","article-title":"Feature extraction based on dbn-svm for tone recognition","volume":"15","author":"chao","year":"2019","journal-title":"JIPS"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"kingma","key":"ref32"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v31i1.11231","article-title":"Inceptionv4, inception-resnet and the impact of residual connections on learning","author":"szegedy","year":"2017","journal-title":"Thirty-First AAAI Conference on Artificial Intelligence"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11265-018-1334-2"},{"key":"ref36","article-title":"Improved tone modeling for mandarin broadcast news speech recognition","author":"lei","year":"2006","journal-title":"Ninth International Conference on Spoken Language Processing"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00097"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"article-title":"Mandarin tone modeling using recurrent neural networks","year":"2017","author":"huang","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854527"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2561"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2293"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.35"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SPED.2017.7990430"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref19","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/89.232612"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2005.03.010"},{"key":"ref6","article-title":"The phonetics of the chinese tonal system","author":"shih","year":"1987","journal-title":"AT&T Bell Labs Technical Memo"},{"article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","year":"2015","author":"ioffe","key":"ref29"},{"key":"ref5","article-title":"Contextual tonal variation in mandarin chinese","author":"xu","year":"1993","journal-title":"ETD Collection for University of Connecticut"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1006\/jpho.1999.0086"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1121\/1.2004881"},{"key":"ref2","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/SpeechProsody.2014-122"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1483"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICFHR-2018.2018.00023"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","article-title":"Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs","volume":"40","author":"chen","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2018.2847291"},{"key":"ref24","first-page":"4700","article-title":"Densely connected convolutional networks","author":"huang","year":"2017","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"article-title":"Yolov3: An incremental improvement","year":"2018","author":"redmon","key":"ref23"},{"key":"ref26","article-title":"Update progress of sinohear: advanced mandarin lvcsr system at nlpr","author":"gao","year":"2000","journal-title":"Sixth International Conference on Spoken Language Processing"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"}],"event":{"name":"2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2021,1,24]]},"location":"Hong Kong","end":{"date-parts":[[2021,1,27]]}},"container-title":["2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9362048\/9362049\/09362063.pdf?arnumber=9362063","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T14:09:27Z","timestamp":1671458967000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9362063\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,24]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/iscslp49672.2021.9362063","relation":{},"subject":[],"published":{"date-parts":[[2021,1,24]]}}}