Neural Architecture Search for LF-MMI Trained Time Delay Neural Networks
Author:
Affiliation:
1. Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong, China
2. Institute of Software, Chinese Academy of Sciences, Beijing, China
Funder
Hong Kong Research Grants Council GRF
Theme-based Research Scheme
Innovation and Technology Fund
Shun Hing Institute of Advanced Engineering
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Subject
Electrical and Electronic Engineering,Acoustics and Ultrasonics,Computer Science (miscellaneous),Computational Mathematics
Link
http://xplorestaging.ieee.org/ielx7/6570655/9657755/09721103.pdf?arnumber=9721103
Reference95 articles.
1. The concrete distribution: A continuous relaxation of discrete random variables;maddison;Proc Int Conf Learn Representations,0
2. A japanese national project on spontaneous speech corpus and processing technology;furui;Proc ASR2000- Autom Speech Recognit Challenges New Millenium ISCA Tut Res Workshop,0
3. Dysarthric speech database for universal access research
4. Single headed attention based sequence-to-sequence model for state-of-the-art results on switchboard-300;tüske;Proc INTERSPEECH,0
5. End-to-end Speech Recognition Using Lattice-free MMI
Cited by 11 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Efficient Automation of Neural Network Design: A Survey on Differentiable Neural Architecture Search;ACM Computing Surveys;2024-06-28
2. Improving the training and application of Chinese language models for low-order grammar;International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2024);2024-06-13
3. A Study of Blockchain and Machine Learning-Enabled IoT Security in Time-Delayed Neural Network Vocal Pattern Recognition to Improve Web-Based Vocal Teaching;Scalable Computing: Practice and Experience;2024-02-24
4. Enhanced Differentiable Architecture Search Based on Asymptotic Regularization;Computers, Materials & Continua;2024
5. Controllable Accented Text-to-Speech Synthesis With Fine and Coarse-Grained Intensity Rendering;IEEE/ACM Transactions on Audio, Speech, and Language Processing;2024
1.学者识别学者识别
2.学术分析学术分析
3.人才评估人才评估
"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370
www.globalauthorid.com
TOP
Copyright © 2019-2024 北京同舟云网络信息技术有限公司 京公网安备11010802033243号 京ICP备18003416号-3