Speech_Emotion_Recognition

Developed and trained 1D and 2D CNN models in Python using TensorFlow and Keras to classify speech emotions from audio data. Implemented data augmentation techniques to increase the size and diversity of the dataset. Evaluated the performance of different model architectures and hyperparameters. Applied feature selection and dimensionality reduction methods such as PCA and LDA to improve the accuracy and efficiency of the models. Explored state-of-the-art techniques from recent research papers to enhance the results, including implementing and evaluating approaches described in existing literature. Conducted a thorough analysis of the performance of these techniques in comparison to our own approach, and documented our findings in two separate reports: one detailing our approach and its results, and another discussing our attempts to replicate the results of an existing paper.