Speech emotion recognition implemented the Convolutional Neural Network to recognize emotion from the audio data files. Furthermore, I have conjointly scrutinized the efficacy of transfer learning for speech emotion recognition employing a pre-trained VGG16 model. Project implementation is carried out on Ryerson Audio-Visual Database of Emotion Speech and Song dataset named as RAVDESS dataset.
Dataset is taken from kaggle : https://www.kaggle.com/uwrfkaggler/ravdess-emotional-speech-audio
