Investigating Sequence-Level Normalisation For CTC-Like End-to-End ASR
Author:
Affiliation:
1. University of Edinburgh,Centre for Speech Technology Research,UK
Funder
Huawei Technologies
Publisher
IEEE
Link
http://xplorestaging.ieee.org/ielx7/9745891/9746004/09746821.pdf?arnumber=9746821
Reference21 articles.
1. Purely Sequence-Trained Neural Networks for ASR Based on Lattice-Free MMI
2. End-to-end speech recognition and keyword search on low-resource languages
3. SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing
4. Intermediate Loss Regularization for CTC-Based Speech Recognition
5. Mask CTC: Non-Autoregressive End-to-End ASR with CTC and Mask Predict
Cited by 5 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. Exploring Dominant Paths in CTC-Like ASR Models: Unraveling the Effectiveness of Viterbi Decoding;2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW);2024-04-14
2. Regarding Topology and Adaptability in Differentiable WFST-Based E2E ASR;2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW);2024-04-14
3. Speech Recognition via CTC-CNN Model;Computers, Materials & Continua;2023
4. Improving Speech Enhancement Framework via Deep Learning;Computers, Materials & Continua;2023
5. End-to-End Speech Recognition Technology Based on Multi-Stream CNN;2022 IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom);2022-12
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