基于TESS和IEMOCAP数据集的MFCC和机器学习的语音情感识别

Q4 Environmental Science Iranian Journal of Botany Pub Date : 2021-03-24 DOI:10.33897/FUJEAS.V1I2.321

Muhammad Zafar Iqbal

{"title":"基于TESS和IEMOCAP数据集的MFCC和机器学习的语音情感识别","authors":"Muhammad Zafar Iqbal","doi":"10.33897/FUJEAS.V1I2.321","DOIUrl":null,"url":null,"abstract":"Our proposed methodology involving MFCC computation along with support Vector machine is used to perform the task of Speech Emotion Recognition (SER) of collectively five emotions named Angry, Happy, Neutral, Pleasant Surprise and Sadness. Two databases are used for this purpose: Toronto Emotion Speech Set (TESS) and Interactive Emotional Dyadic Motion Capture (IEMOCAP). We achieved 97% accuracy with TESS and 86% accuracy with IEMOCAP respectively.","PeriodicalId":36255,"journal":{"name":"Iranian Journal of Botany","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2021-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"MFCC and Machine Learning Based Speech Emotion Recognition Over TESS and IEMOCAP Datasets\",\"authors\":\"Muhammad Zafar Iqbal\",\"doi\":\"10.33897/FUJEAS.V1I2.321\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Our proposed methodology involving MFCC computation along with support Vector machine is used to perform the task of Speech Emotion Recognition (SER) of collectively five emotions named Angry, Happy, Neutral, Pleasant Surprise and Sadness. Two databases are used for this purpose: Toronto Emotion Speech Set (TESS) and Interactive Emotional Dyadic Motion Capture (IEMOCAP). We achieved 97% accuracy with TESS and 86% accuracy with IEMOCAP respectively.\",\"PeriodicalId\":36255,\"journal\":{\"name\":\"Iranian Journal of Botany\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-03-24\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Iranian Journal of Botany\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.33897/FUJEAS.V1I2.321\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"Environmental Science\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Iranian Journal of Botany","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.33897/FUJEAS.V1I2.321","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"Environmental Science","Score":null,"Total":0}

引用次数: 1

摘要

我们提出的方法包括MFCC计算和支持向量机来执行语音情感识别(SER)的任务，这五种情绪分别是愤怒、快乐、中性、惊喜和悲伤。为此使用了两个数据库:多伦多情感语音集(TESS)和交互式情感二元动作捕捉(IEMOCAP)。TESS的准确率为97%，IEMOCAP的准确率为86%。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

MFCC and Machine Learning Based Speech Emotion Recognition Over TESS and IEMOCAP Datasets

Our proposed methodology involving MFCC computation along with support Vector machine is used to perform the task of Speech Emotion Recognition (SER) of collectively five emotions named Angry, Happy, Neutral, Pleasant Surprise and Sadness. Two databases are used for this purpose: Toronto Emotion Speech Set (TESS) and Interactive Emotional Dyadic Motion Capture (IEMOCAP). We achieved 97% accuracy with TESS and 86% accuracy with IEMOCAP respectively.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊