首页> 外文OA文献 >Evaluation of error- and correlation-based loss functions for multitask learning dimensional speech emotion recognition

【2h】

Evaluation of error- and correlation-based loss functions for multitask learning dimensional speech emotion recognition

机译：基于误差和相关的多任务学习尺寸语音情感识别的误差函数评估

代理获取

本网站仅为用户提供外文OA文献查询和代理获取服务，本网站没有原文。下单后我们将采用程序或人工为您竭诚获取高质量的原文，但由于OA文献来源多样且变更频繁，仍可能出现获取不到、文献不完整或与标题不符等情况，如果获取不到我们将提供退款服务。请知悉。

页面导航

著录项
引文网络
相似文献
相关主题

著录项

作者
B T Atmaja; M Akagi;
展开▼
作者单位

展开▼
年度 2021
总页数
原文格式 PDF
正文语种
中图分类

相似文献

外文文献
中文文献
专利

1. Speech emotion recognition using hybrid spectral-prosodic features of speech signal/glottal waveform, metaheuristic-based dimensionality reduction, and Gaussian elliptical basis function network classifier [J] . Daneshfar Fatemeh, Kabudian Seyed Jahanshah, Neekabadi Abbas Applied Acoustics . 2020,第Sepa期

机译：语音情感识别使用语音信号/光学波形的混合谱 - 韵律特征，基于血管训练的维数减少和高斯椭圆形基函数网络分类器
2. Evaluating deep learning architectures for Speech Emotion Recognition [J] . Fayek Haytham M., Lech Margaret, Cavedon Lawrence Neural Networks: The Official Journal of the International Neural Network Society . 2017,第期

机译：评估语音情感识别的深度学习架构
3. Learning With Learned Loss Function: Speech Enhancement With Quality-Net to Improve Perceptual Evaluation of Speech Quality [J] . Fu Szu-Wei, Liao Chien-Feng, Tsao Yu IEEE signal processing letters . 2020,第期

机译：学习损失职能学习：语音增强质量网改善语音质量的感知评价
4. Dimensional Speech Emotion Recognition from Acoustic and Text Features Using Multitask Learning [C] . Bagus Tris Atmaja, Masato Akagi 日本音響学会;日本音響学会研究発表会 . 2020

机译：使用多任务学习的声学和文本特征的维度语音情感识别
5. Design of loss functions and feature transformation for minimum classification error based automatic speech recognition [D] . Ratnagiri, Madhavi Vedula 2011

机译：基于最小分类误差的自动语音识别损失函数设计和特征变换
6. Multi-Path and Group-Loss-Based Network for Speech Emotion Recognition in Multi-Domain Datasets [O] . Kyoung Ju Noh, Chi Yoon Jeong, Jiyoun Lim, 2021

机译：基于多路径和组丢失的语音情感识别网络中的多域数据集
7. EEG Signal Discrimination using Non-linear Dynamics in the EMD Domain S. M. Shafiul Alam,S. M. Shafiul Alam,Aurangozeb, and Syed TarekShahriar Abstract—An EMD-chaos based approach is proposed todiscriminate EEG signals corresponding to healthy persons,and epileptic patients during seizure-free intervals and seizureattacks. An electroencephalogram (EEG) is first empiricallydecomposed to intrinsic mode functions (IMFs). The nonlineardynamics of these IMFs are quantified in terms of the largestLyapunov exponent (LLE) and correlation dimension (CD).This chaotic analysis in EMD domain is applied to a large groupof EEG signals corresponding to healthy persons as well asepileptic patients (both with and without seizure attacks). It isshown that the values of the obtained LLE and CD exhibitfeatures by which EEG for seizure attacks can be clearlydistinguished from other EEG signals in the EMD domain.Thus, the proposed approach may aid researchers in developingeffective techniques to predict seizure activities. Index Terms—Electroencephalogram (EEG), empiricalmode decomposition (EMD), largest Lyapunov exponent (LLE),correlation dimension (CD), epileptic seizures. The Authors are with the Electrical and Electronic EngineeringDepartment, Bangladesh University of Engineering and Technology,Dhaka-1000, Bangladesh (e-mail: imamul@eee.buet.ac.bd) PDF Cite: S. M. Shafiul Alam,S. M. Shafiul Alam,Aurangozeb, and Syed Tarek Shahriar, "EEG Signal Discrimination using Non-linear Dynamics in the EMD Domain," International Journal of Computer and Electrical Engineering vol. 4, no. 3, pp. 326-330, 2012. PREVIOUS PAPER Perception of Emotions Using Constructive Learningthrough Speech NEXT PAPER Physical Layer Impairments Aware OVPN Connection Selection Mechanisms Copyright © 2008-2013. International Association of Computer Science and Information Technology Press (IACSIT Press) [O] . S. M. Shafiul Alam, Syed TarekShahriar 2012

机译：EEG信号在EMD域S. S. Shafiul Alam，S中的非线性动力学使用非线性动力学。 M. Shafiul Alam，Aurangozeb和Syed Tarekshahriar摘要 - 基于EMD Chaos的方法，提出了对应于健康人的EEG信号，癫痫发作期间的癫痫患者和Seizureattacks。脑电图（EEG）首先被凭经上分解为内在模式功能（IMF）。这些IMF的非线性动力学在最大范围的指数（LLE）和相关尺寸（CD）方面是量化的。本域中的混沌分析应用于与健康人相对应的大型脑电图（Asepileptic患者）（两者都有癫痫发作）。因此，所获得的LLE和CD表展的价值可以从EMD领域的其他EEG信号中清晰地区分脑电图的表达展示。本拟议的方法可以帮助研究人员以预测癫痫发作的癫痫发作技术。索引术语 - 脑电图（EEG），仿真态分解（EMD），最大的Lyapunov指数（LLE），相关维度（CD），癫痫发作。作者与电气电子和电子工程公司，孟加拉国工程和技术大学，孟加拉国达卡 - 1000（电子邮件：imamul@eee.buet.ac.bd）pdf cite：s. m. shafiul Alam，s。 M. Shafiul Alam，Aurangozeb和Syed Tarek Shahriar，“EEG信号歧视在EMD领域的非线性动态，”计算机电气工程卷国际杂志。 4，不。 3，pp。326-330,2012，上一篇论文对情绪的看法，使用建设性的学习言论下一篇论文物理层障碍意识到OVPN连接选择机制版权所有©2008-2013。国际计算机科学与信息技术协会出版社（IACSIT Press）

Evaluation of error- and correlation-based loss functions for multitask learning dimensional speech emotion recognition

著录项

引文网络

相似文献

相关主题

期刊订阅