Emotion recognition through speech is one of the fundamental approaches for human interaction. Speech modulations stipulate different emotions and context. In this paper, we propose modified dense convolutional networks (modified DenseNet201) for emotion detection from speech using its paralinguistic features such as vocal tract features. The proposed network performs emotion classification from speech using spectrograms of its audio files. The proposed network outperforms other alternative models like residual networks, AlexNet, VGG16, SVM, XGBoost, boosted random forest etc. for emotion classification from speech. Moreover, the proposed network surpasses all other existing methods proposed in the literature and obtains state-of-the-art results in most of the cases. Further, the proposed network has been successfully validated on two different language datasets: ‘EmoDB’ and ‘SAVEE’ which qualifies it as a language-independent emotion detection system from speech.

通过语音进行情感识别是人类交互的基本方法之一。语音调制规定了不同的情绪和语境。在本文中，我们提出了改进的密集卷积网络（改进的 DenseNet201），使用其副语言特征（如声道特征）从语音中检测情感。提议的网络使用其音频文件的频谱图从语音中执行情感分类。所提出的网络在语音情感分类方面优于其他替代模型，如残差网络、AlexNet、VGG16、SVM、XGBoost、增强随机森林等。此外，所提出的网络超越了文献中提出的所有其他现有方法，并在大多数情况下获得了最先进的结果。更多，