欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
该文将混合蛙跳算法（SELA）优化方法应用于人工神经网络训练中,对6种语音情感进行了语音情感特征的分析与识别。研究了谐波噪声比特征随情感类别的变化特性。利用混合蛙跳算法训练随机产生的初始数据优化神经网络的连接权值,快速实现了网络收敛。实验比较了BP神经网络、RBF神经网络和SFLA神经网络的语音情感识别性能。结果表明,SFLA神经网络的平均识别率分别高于BP神经网络和RBF神经网络4.7%和4.3%。
英文摘要：
The shuffled frog-leaping algorithm（SFLA） is applied to the speech emotion recognition in neural network training.The freatures of the six speech emotions are extracted and recognized.The changes of harmonics-to-noise ratio（HNR） features with different emotions are studied.The random initial data trained by the SFLA is used to optimize the connection weights and thresholds of the neural network,and the network can converge fast.The recognition capability of the BP,RBF and SFLA neural networks are compared experimentally.The results show that the recognition ratio of the SFLA neural network is 4.7% better than that of BP neural network and 4.3% better than that of the RBF neural network.
同期刊论文项目
同项目期刊论文
Blind Multiple Access Interference Suppression Algorithm Based on Relaxed Subgradient Projection for
Two-dimensional canonical correlation analysis and its application in small sample size face recogni
期刊信息
位置：