Improving Hybrid CTC/Attention End-to-End Speech Recognition with Pretrained Acoustic and Language Models-Reference-Cited by-同舟云学术

登录注册会员服务联系我们

Improving Hybrid CTC/Attention End-to-End Speech Recognition with Pretrained Acoustic and Language Models

Published:2021-12-13 Issue: Volume: Page:
ISSN:
Container-title:2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)
language:
Short-container-title:

Author:

Deng Keqi¹,Cao Songjun¹,Zhang Yike¹,Ma Long¹

Affiliation:

1. Tencent Cloud Xiaowei,Beijing,China

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/9687821/9687855/09688009.pdf?arnumber=9688009

Reference41 articles.

1. Accurate, large minibatch SGD: training imagenet in 1 hour;goyal;CoRR,2017

2. UER: An Open-Source Toolkit for Pre-training Models

3. Leveraging Unpaired Text Data for Training End-To-End Speech-to-Intent Systems

4. Self-Training and Pre-Training are Complementary for Speech Recognition

5. Joint Masked CPC And CTC Training For ASR

Cited by 20 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. Automatic speech recognition using advanced deep learning approaches: A survey;Information Fusion;2024-09

2. Arabic Automatic Speech Recognition: Challenges and Progress;Speech Communication;2024-09

3. Decoupled structure for improved adaptability of end-to-end models;Speech Communication;2024-09

4. Extending speech emotion recognition systems to non-prototypical emotions using mixed-emotion model;Expert Systems with Applications;2024-09

5. Factorized and progressive knowledge distillation for CTC-based ASR models;Speech Communication;2024-05

同舟云学术

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