Cross-Corpus Training Strategy for Speech Emotion Recognition Using Self-Supervised Representations

Author:

Pastor Miguel A.1,Ribas Dayana1ORCID,Ortega Alfonso1ORCID,Miguel Antonio1ORCID,Lleida Eduardo1ORCID

Affiliation:

1. ViVoLab, Aragón Institute for Engineering Research (I3A), University of Zaragoza, 50009 Zaragoza, Spain

Abstract

Speech Emotion Recognition (SER) plays a crucial role in applications involving human-machine interaction. However, the scarcity of suitable emotional speech datasets presents a major challenge for accurate SER systems. Deep Neural Network (DNN)-based solutions currently in use require substantial labelled data for successful training. Previous studies have proposed strategies to expand the training set in this framework by leveraging available emotion speech corpora. This paper assesses the impact of a cross-corpus training extension for a SER system using self-supervised (SS) representations, namely HuBERT and WavLM. The feasibility of training systems with just a few minutes of in-domain audio is also analyzed. The experimental results demonstrate that augmenting the training set with EmoDB (German), RAVDESS, and CREMA-D (English) datasets leads to improved SER accuracy on the IEMOCAP dataset. By combining a cross-corpus training extension and SS representations, state-of-the-art performance is achieved. These findings suggest that the cross-corpus strategy effectively addresses the scarcity of labelled data and enhances the performance of SER systems.

Funder

European Union

European Union “NextGenerationEU”/PRTR

Government of Aragon

Publisher

MDPI AG

Subject

Fluid Flow and Transfer Processes,Computer Science Applications,Process Chemistry and Technology,General Engineering,Instrumentation,General Materials Science

Cited by 7 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. Optimized Multimodal Emotional Recognition Using Long Short-Term Memory;Contemporaneity of English Language and Literature in the Robotized Millennium;2024-07-01

2. Improving Speech Emotion Recognition through Hierarchical Classification and Text Integration for Enhanced Emotional Analysis and Contextual Understanding;2024 International Joint Conference on Neural Networks (IJCNN);2024-06-30

3. Self-Labeling Learning Ensemble via Deep Recurrent Neural Network and Self-Representation for Speech Emotion Recognition;International Journal of Pattern Recognition and Artificial Intelligence;2024-06-22

4. BSER: A Learning Framework for Bangla Speech Emotion Recognition;2024 6th International Conference on Electrical Engineering and Information & Communication Technology (ICEEICT);2024-05-02

5. Automatic Voice Disorder Detection from a Practical Perspective;Journal of Voice;2024-05

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