Urdu Speech Emotion Recognition: A Systematic Literature Review

Author:

Taj Soonh1ORCID,Mujtaba Ghulam1ORCID,Daudpota Sher Muhammad1ORCID,Mughal Muhammad Hussain1ORCID

Affiliation:

1. Department of Computer Science, Sukkur IBA University

Abstract

Research on Speech Emotion Recognition is becoming more mature day by day, and a lot of research is being carried out on Speech Emotion Recognition in resource-rich languages like English, German, French, and Chinese. Urdu is among the top 10 languages spoken worldwide. Despite its importance, few studies have worked on Urdu Speech emotion as Urdu is recognized as a resource-poor language. The Urdu language lacks publicly available datasets, and for this reason, few researchers have worked on Urdu Speech Emotion Recognition. To the best of our knowledge, no review has been found on Urdu Speech Emotion recognition. This study is the first systematic literature review on Urdu Speech Emotion Recognition, and the primary goal of this study is to provide a detailed analysis of the literature on Urdu Speech Emotion Recognition which includes the datasets, features, pre-processing, approaches, performance metrics, and validation methods used for Urdu Speech Emotion Recognition. This study also highlights the challenges and future directions for Urdu Speech Emotion Recognition.

Funder

National Research Program for Universities

Higher Education Commission

Publisher

Association for Computing Machinery (ACM)

Subject

General Computer Science

Reference77 articles.

1. Martín Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, and Michael Isard. 2016. TensorFlow: A System for Large-Scale Machine Learning. In Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation (Savannah, GA, USA) (OSDI'16). USENIX Association, 265–283.

2. Deep learning techniques for speech emotion recognition, from databases to models;Joze Abbaschian Babak;Sensors,2021

3. Noise reduction of speech signal using wavelet transform with modified universal threshold;Aggarwal Rajeev;International Journal of Computer Applications,2011

4. Speech emotion recognition: Emotional models, databases, features, preprocessing methods, supporting modalities, and classifiers;Berkehan Akçay Mehmet;Speech Communication,2020

5. Emotion recognition in never-seen languages using a novel ensemble method with emotion profiles;Marcelo Albornoz Enrique;IEEE Transactions on Affective Computing,2015

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

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