{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T14:05:05Z","timestamp":1760709905786,"version":"3.28.0"},"reference-count":30,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,11]]},"DOI":"10.1109\/iscslp.2018.8706661","type":"proceedings-article","created":{"date-parts":[[2019,5,20]],"date-time":"2019-05-20T22:58:35Z","timestamp":1558393115000},"page":"369-373","source":"Crossref","is-referenced-by-count":22,"title":["Comparable Study Of Modeling Units For End-To-End Mandarin Speech Recognition"],"prefix":"10.1109","author":[{"given":"Wei","family":"Zou","sequence":"first","affiliation":[]},{"given":"Dongwei","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Shuaijiang","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Guilin","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Xiangang","family":"Li","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref30","article-title":"An empirical exploration of ctc acoustic models","author":"miao","year":"2016","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref11","article-title":"Towards better decoding and language model integration in sequence to sequence models","author":"chorowski","year":"2016","journal-title":"arXiv preprint arXiv 1612 02695"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-334"},{"key":"ref13","article-title":"Attention-based end-to-end speech recognition in mandarin","author":"shan","year":"2017","journal-title":"arXiv preprint arXiv 1707 07816"},{"key":"ref14","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref15","article-title":"Advances in joint ctc-attention based end-to-end speech recognition with a deep cnn encoder and rnn-lm","author":"hori","year":"2017","journal-title":"arXiv preprint arXiv 1706 02737"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462492"},{"key":"ref18","article-title":"Large vocabulary mandarin speech recognition with different approaches in modeling tones","author":"chang","year":"2000","journal-title":"Sixth International Conference on Spoken Language Processing"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1016\/j.neucom.2014.07.087","article-title":"A comparative study on selecting acoustic modeling units in deep neural networks based large vocabulary chinese speech recognition","volume":"170","author":"xiangang","year":"2015","journal-title":"Neurocomputing"},{"key":"ref28","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"key":"ref4","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","author":"amodei","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref27","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"arXiv preprint arXiv 1607 06450"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref29","article-title":"Tensorflow: Large-scale machine learning on heterogeneous distributed systems","author":"abadi","year":"2016","journal-title":"arXiv preprint arXiv 1603 04467"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref8","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"International Conference on Machine Learning"},{"key":"ref7","article-title":"State-of-the-art speech recognition with sequence-to-sequence models","author":"chiu","year":"2017","journal-title":"arXiv preprint arXiv 1712 01769"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"939","DOI":"10.21437\/Interspeech.2017-233","article-title":"A comparison of sequence-to-sequence models for speech recognition","author":"prabhavalkar","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639345"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1137"},{"key":"ref22","article-title":"New methods in continuous mandarin speech recognition","author":"chen","year":"1997","journal-title":"Fifth European Conference on Speech Communication and Technology"},{"key":"ref21","first-page":"61","article-title":"Context dependent initial\/final acoustic modeling for continuous chinese speech recognition","volume":"44","author":"li","year":"2004","journal-title":"Journal of Tsinghua University"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"724","DOI":"10.1007\/11939993_73","article-title":"Hkust\/mts: A very large scale mandarin telephone speech corpus","author":"liu","year":"2006","journal-title":"Chinese Spoken Language Processing"},{"key":"ref23","article-title":"Context dependent syllable acoustic model for continuous chinese speech recognition","author":"wu","year":"2007","journal-title":"Eighth Annual Conference of the International Speech Communication Association"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178838"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953077"}],"event":{"name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2018,11,26]]},"location":"Taipei City, Taiwan","end":{"date-parts":[[2018,11,29]]}},"container-title":["2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8701133\/8706262\/08706661.pdf?arnumber=8706661","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,23]],"date-time":"2020-08-23T23:10:53Z","timestamp":1598224253000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8706661\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/iscslp.2018.8706661","relation":{},"subject":[],"published":{"date-parts":[[2018,11]]}}}