Building Robust Spoken Language Understanding by Cross Attention Between Phoneme Sequence and ASR Hypothesis-Reference-Cited by-同舟云学术

登录注册会员服务联系我们

Building Robust Spoken Language Understanding by Cross Attention Between Phoneme Sequence and ASR Hypothesis

Published:2022-05-23 Issue: Volume: Page:
ISSN:
Container-title:ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
language:
Short-container-title:

Author:

Wang Zexun¹,Le Yuquan¹,Zhu Yi¹,Zhao Yuming¹,Feng Mingchao¹,Chen Meng¹,He Xiaodong¹

Affiliation:

1. JD AI,Beijing,China

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/9745891/9746004/09747198.pdf?arnumber=9747198

Reference23 articles.

1. Spoken Language Intent Detection Using Confusion2Vec

2. Improving spoken language understanding by exploiting asr n-best hypotheses;li,2020

3. ASR N-Best Fusion Nets

4. Rescoring N-Best Speech Recognition List Based on One-on-One Hypothesis Comparison Using Encoder-Classifier Model

5. Improved Deep Duel Model for Rescoring N-Best Speech Recognition List Using Backward LSTMLM and Ensemble Encoders

Cited by 2 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. MCRSpell: A metric learning of correct representation for Chinese spelling correction;Expert Systems with Applications;2024-03

2. Contrastive Learning Based ASR Robust Knowledge Selection For Spoken Dialogue System;INTERSPEECH 2023;2023-08-20

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