On Lattice-Free Boosted MMI Training of HMM and CTC-Based Full-Context ASR Models-Reference-Cited by-同舟云学术

登录注册会员服务联系我们

On Lattice-Free Boosted MMI Training of HMM and CTC-Based Full-Context ASR Models

Published:2021-12-13 Issue: Volume: Page:
ISSN:
Container-title:2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)
language:
Short-container-title:

Author:

Zhang Xiaohui¹,Manohar Vimal¹,Zhang David¹,Zhang Frank¹,Shi Yangyang¹,Singhal Nayan¹,Chan Julian¹,Peng Fuchun¹,Saraf Yatharth¹,Seltzer Mike¹

Affiliation:

1. Facebook AI,USA

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/9687821/9687855/09688056.pdf?arnumber=9688056

Reference42 articles.

1. Emformer: Efficient Memory Transformer Based Acoustic Model for Low Latency Streaming Speech Recognition

2. Specaugment: A simple data augmentation method for automatic speech recog-nition;park;ArXiv Preprint,2019

3. Semi-supervised maximum mutual information training of deep neural network acoustic models

4. Faster, Simpler and More Accurate Hybrid ASR Systems Using Wordpieces

5. SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing

Cited by 8 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. Less Peaky and More Accurate CTC Forced Alignment by Label Priors;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

2. Investigating The Effect of Language Models in Sequence Discriminative Training For Neural Transducers;2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU);2023-12-16

3. End-To-End Training of a Neural HMM with Label and Transition Probabilities;2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU);2023-12-16

4. CAST: Context-association architecture with simulated long-utterance training for mandarin speech recognition;Speech Communication;2023-11

5. Lattice-Free Sequence Discriminative Training for Phoneme-Based Neural Transducers;ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2023-06-04

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