Speech Emotion Recognition System using DenseNet – 121 on MFCC Features
Bibliographic record
Abstract
Today the Speech Emotion Recognition (SER) technology continues to evolve, it promises to revolutionize multiple domains by creating more empathetic, responsive, and effective human-computer interactions that better provide to users’ emotional needs. Speech Emotion Recognition (SER) is continuously improving. In this system, SER was implemented using the DenseNet-121 architecture. The system was tested on three benchmark datasets: the Toronto Emotional Speech Set (TESS), the Surrey Audio-Visual Expressed Emotion (SAVEE), and the Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS). Experiments used three dataset combinations: TESS + SAVEE, TESS + RAVDESS, and TESS + RAVDESS + SAVEE. Features were extracted using Mel-Frequency Cepstral Coefficients (MFCCs) with 13, 32, and 40 coefficients. The data was split 80% for training and 20% for validation and testing. The TESS + SAVEE combination classified seven emotions: angry, disgust, fear, happy, neutral, sad, and surprise. The TESS + RAVDESS + SAVEE combination classified eight emotions: angry, calm, disgust, fear, happy, neutral, sad, and surprise. Higher-dimensional MFCCs (40 coefficients) gave the best performance. The TESS + SAVEE setup achieved a maximum accuracy of 95.43%. These results demonstrate that integrating MFCC-based features with DenseNet-121 provides a robust framework for accurately recognizing a wide range of emotional states from speech, highlighting its potential for real-world emotion-aware applications.
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 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.004 |
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".