The DKU Audio-Visual Wake Word Spotting System for the 2021 MISP Challenge
Author:
Affiliation:
1. School of Computer Science, Wuhan University,Wuhan,China
2. Data Science Research Center, Duke Kunshan University,Kunshan,China
Funder
National Natural Science Foundation of China
Fundamental Research Funds for the Central Universities
Publisher
IEEE
Link
http://xplorestaging.ieee.org/ielx7/9745891/9746004/09747216.pdf?arnumber=9747216
Reference29 articles.
1. Wake Word Detection with Streaming Transformers
2. Domain Aware Training for Far-Field Small-Footprint Keyword Spotting
3. Learning to Detect Keyword Parts and Whole by Smoothed Max Pooling
4. Audio-Visual Keyword Spotting Based on Multidimensional Convolutional Neural Network
5. The First Multimodal Information Based Speech Processing (Misp) Challenge: Data, Tasks, Baselines And Results
Cited by 10 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. The Whu Wake Word Lipreading System for the 2024 Chat-Scenario Chinese Lipreading Challenge;2024 IEEE International Conference on Multimedia and Expo Workshops (ICMEW);2024-07-15
2. Exploring Semi-Supervised, Subcategory Classification and Subwords Alignment for Visual Wake Word Spotting;2024 IEEE International Conference on Multimedia and Expo Workshops (ICMEW);2024-07-15
3. Enhancing Visual Wake Word Spotting with Pretrained Model and Feature Balance Scaling;2024 IEEE International Conference on Multimedia and Expo Workshops (ICMEW);2024-07-15
4. MLCA-AVSR: Multi-Layer Cross Attention Fusion Based Audio-Visual Speech Recognition;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14
5. Robust Wake Word Spotting With Frame-Level Cross-Modal Attention Based Audio-Visual Conformer;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14
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