Speech Emotion Recognition: A Human-Centric Framework with Enhanced Data Augmentation and Lightweight CNN
Bibliographic record
Abstract
Speech Emotion Recognition (SER) has significant potential to enhance human-computer interaction, particularly in real-time applications. However, deploying SER models on resource-constrained edge devices necessitates efficient and compact solutions. This paper proposes a lightweight Convolutional Neural Network (CNN) framework enhanced with targeted audio augmentation techniques and optimized feature representation. The preprocessing pipeline incorporates controlled pitch shifting, time stretching, and Gaussian noise injection to improve data diversity. Thirteen Mel-Frequency Cepstral Coefficients (MFCCs), along with their first and second-order derivatives, are extracted and subsequently reduced using Principal Component Analysis (PCA) to form 32 by 32 feature maps. Trained on the Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) dataset, the proposed model achieves 72 percent of classification accuracy, demonstrating a favorable trade-off between performance and computational efficiency. Comparative evaluations against hybrid and attention-based architectures highlight the model's suitability for edge deployment. Future work includes integrating lightweight attention mechanisms and extending validation across more diverse emotion datasets.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.016 | 0.001 |
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; both teacher heads agree on what is shown here.
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".