acoustic signal processing; emotion recognition; neural nets; speech processing; 2D black images; 2D graphical representation; MFCC-G; MFCC-S; OMC-DNN; TEO-G; TEO-S; acoustic speech features; categorical emotions; glottal energy characteristics; optimized multichannel deep neural network; single-channel DNN; single-channel benchmark classifiers; speech emotion recognition; speech spectrum; white images; Accuracy; Artificial neural networks; Benchmark testing; Emotion recognition; Speech; Speech recognition; 2D features; deep neural network; emotion recognition; multichannel speech classification;
机译:使用深度经常性神经网络具有声学特征的情感认识
机译:学习深层卷积神经网络的深层双耳陈述,用于自发言论情绪识别
机译:基于深度卷积神经网络的深浅特征融合在语音情感识别中的应用
机译:使用深度神经网络学习语音表达和年龄/性别识别的话语级表示
机译:使用深度神经网络的表情异常语音识别和离线手写识别。
机译:利用深卷积神经网络对语音情感识别的特征选择算法的影响
机译:利用深层学习算法具有有效声学特征的语音情感识别系统研究