Improving Scheduled Sampling for Neural Transducer-Based ASR-Reference-Cited by-同舟云学术

登录注册会员服务联系我们

Improving Scheduled Sampling for Neural Transducer-Based ASR

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:

Moriya Takafumi¹,Ashihara Takanori¹,Sato Hiroshi¹,Matsuura Kohei¹,Tanaka Tomohiro¹,Masumura Ryo¹

Affiliation:

1. NTT Corporation,Japan

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/10094559/10094560/10095826.pdf?arnumber=10095826

Reference32 articles.

1. Internal Language Model Training for Domain-Adaptive End-To-End Speech Recognition

2. Internal Language Model Estimation for Domain-Adaptive End-to-End Speech Recognition

3. A Comparative Study on Neural Architectures and Training Methods for Japanese Speech Recognition

4. Librispeech Transducer Model with Internal Language Model Prior Correction

5. The Rwth Asr System for Ted-Lium Release 2: Improving Hybrid Hmm With Specaugment

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

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