Audio Emotion Detection Application Utilizing AWS Cloud
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.003 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".