ScSer: Supervised Contrastive Learning for Speech Emotion Recognition using Transformers
Author:
Affiliation:
1. National Institute of Technology Calicut,Department of Computer Science and Engineering,Calicut,India
2. ABV - Indian Institute of Information Technology and Management Gwalior,Computational Intelligence and Data Mining Research Lab,Gwalior,India
Publisher
IEEE
Link
http://xplorestaging.ieee.org/ielx7/9869420/9869438/09869453.pdf?arnumber=9869453
Reference26 articles.
1. Deep convolutional recurrent neural network with attention mechanism for robust speech emotion recognition
2. Data Augmenting Contrastive Learning of Speech Representations in the Time Domain;kharitonov,2020
3. Supervised contrastive learning;khosla;Advances in neural information processing systems,2020
4. Towards speech emotion recognition;kim;the wild” using aggregated corpora and deep multi-task learning,2017
5. Variational autoencoders for learning latent representations of speech emotion: A preliminary study;latif,2017
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. Multimodal and Multitask Learning with Additive Angular Penalty Focus Loss for Speech Emotion Recognition;International Journal of Intelligent Systems;2023-10-17
2. Intermediate-Task Learning with Pretrained Model for Synthesized Speech MOS Prediction;2023 IEEE International Conference on Multimedia and Expo (ICME);2023-07
3. Multi-branch feature learning based speech emotion recognition using SCAR-NET;Connection Science;2023-04-27
4. Emotional Speech Synthesis using End-to-End neural TTS models;2022 18th International Computer Engineering Conference (ICENCO);2022-12-29
5. Evaluation Of Performance Of Artificial Intelligence System During Voice Recognition In Social Conversations using NLP;2022 13th International Conference on Computing Communication and Networking Technologies (ICCCNT);2022-10-03
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