Streaming End-to-End ASR Using CTC Decoder and DRA for Linguistic Information Substitution-Reference-Cited by-同舟云学术

登录注册会员服务联系我们

Streaming End-to-End ASR Using CTC Decoder and DRA for Linguistic Information Substitution

Published:2023-10-31 Issue: Volume: Page:
ISSN:
Container-title:2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)
language:
Short-container-title:

Author:

Takagi Tatsunari¹,Ogawa Atsunori²,Kitaoka Norihide¹,Wakabayashi Yukoh¹

Affiliation:

1. Toyohashi University of Technology,Japan

2. Nippon Telegraph and Telephone Corporation,Japan

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/10317071/10317095/10317583.pdf?arnumber=10317583

Reference21 articles.

1. Massively Multilingual Shallow Fusion with Large Language Models

2. Adaptable Multi-Domain Language Model for Transformer ASR

3. Advancing RNN Transducer Technology for Speech Recognition

4. A Density Ratio Approach to Language Model Fusion in End-to-End Automatic Speech Recognition

5. Personalized speech recognition on mobile devices

Cited by 1 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. Recognition of target domain Japanese speech using language model replacement;EURASIP Journal on Audio, Speech, and Music Processing;2024-07-20

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