Audio Emotion Detection Application Utilizing AWS Cloud

Introduction: Many applications today seek to understand user emotions through audio data, enhancing user engagement and experience. However, existing systems often lack the efficiency needed for real-time processing and accurate emotion detection. Developing a system that detects emotions from audio file uploads necessitates an infrastructure that can scale to meet user demands, ensure secure data processing, and integrate artificial intelligence services for emotion analysis. The key challenge is to design a cloud architecture that is scalable, secure, cost-efficient, and capable of analyzing emotions in audio files while delivering results promptly to users. Objective: To address the abovementioned challenges, this paper proposes a cloud-based system that allows users to upload audio files, analyses them to identify emotions (such as anger, calmness, disgust, fear, happiness, neutrality, sadness, surprise, etc.), and returns the detected emotions to the user in a timely manner. Methods: Two open datasets, Surrey Audio-Visual Expressed Emotion (SAVEE) and Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS), were collected for training and testing the employed models using AWS cloud services. Results: The proposed method performed better than the existing methods for RAVDESS and SAVEE datasets by achieving a weighted accuracy of 93% and 94%, respectively, compared to four baselines, which obtained weighted accuracy of 71%, 73%, and 77%, respectively, for RAVDESS dataset, and 67% for SAVEE dataset. Conclusion: The system architecture has been crafted to be scalable and flexible, making it suitable for various applications, thus greatly enhancing user interactions.