Hierarchical Softmax for End-To-End Low-Resource Multilingual Speech Recognition-Reference-Cited by-同舟云学术

登录注册会员服务联系我们

Hierarchical Softmax for End-To-End Low-Resource Multilingual Speech Recognition

Published:2023-06-04 Issue: Volume: Page:
ISSN:
Container-title:ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
language:
Short-container-title:

Author:

Liu Qianying¹,Gong Zhuo²,Yang Zhengdong¹,Yang Yuhang³,Li Sheng⁴,Ding Chenchen⁴,Minematsu Nobuaki²,Huang Hao³,Cheng Fei¹,Chu Chenhui¹,Kurohashi Sadao¹

Affiliation:

1. Kyoto University,Graduate School of Informatics,Kyoto,Japan

2. The University of Tokyo,Graduate School of Engineering,Department of EEIS,Tokyo,Japan

3. Xinjiang University,School of Information Science and Engineering,Urumqi,China

4. National Institute of Information and Communications Technology (NICT),Kyoto,Japan

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/10094559/10094560/10095133.pdf?arnumber=10095133

Reference31 articles.

1. Unsupervised speech recognition;baevski;Proc Neurlps,2021

2. wav2vec2.0: A framework for self-supervised learning of speech representations;baevski;Proc Neurlps,2020

3. WeNet: Production Oriented Streaming and Non-Streaming End-to-End Speech Recognition Toolkit

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