Real-Time Speech Emotion Recognition Using Deep Learning and Data Augmentation

Author:

Barhoumi Chawki1,Ayed Yassine Ben2

Affiliation:

1. National School of Electronics and Telecommunications of Sfax

2. Multimedia, InfoRmation systems and Advanced Computing Laboratory

Abstract

Abstract In human-human interactions, detecting emotions is often easy as it can be perceived through facial expressions, body gestures, or speech. However, in human-machine interactions, detecting human emotion can be a challenge. To improve this interaction, the term 'speech emotion recognition' has emerged, with the goal of recognizing emotions solely through vocal intonation. In this work, we propose a speech emotion recognition system based on deep learning approaches and two efficient data augmentation techniques (noise addition and spectrogram shifting). To evaluate the proposed system, we used three different datasets: TESS, EmoDB, and RAVDESS. We employe several algorithms such as Mel Frequency Cepstral Coefficients (MFCC), Zero Crossing Rate (ZCR), Mel spectrograms, Root Mean Square Value (RMS), and chroma to select the most appropriate vocal features that represent speech emotions. To develop our speech emotion recognition system, we use three different deep learning models, including MultiLayer Perceptron (MLP), Convolutional Neural Network (CNN), and a hybrid model that combines CNN with Bidirectional Long-Short Term Memory (Bi-LSTM). By exploring these different approaches, we were able to identify the most effective model for accurately identifying emotional states from speech signals in real-time situation. Overall, our work demonstrates the effectiveness of the proposed deep learning model, specifically based on CNN+BiLSTM, and the used two data augmentation techniques for the proposed real-time speech emotion recognition.

Publisher

Research Square Platform LLC

Cited by 2 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. Machine Learning Approach for Detection of Speech Emotions for RAVDESS Audio Dataset;2024 Fourth International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT);2024-01-11

2. Deep Learning Algorithms for Speech Emotion Recognition with Hybrid Spectral Features;SN Computer Science;2023-11-16

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