Speech Emotion Recognition Using Multi-Domain Acoustic Features and Hybrid Machine Learning Model
Bibliographic record
Abstract
Accurately recognizing human emotions from speech remains a challenging task due to the complex interplay of linguistic and paralinguistic cues, speaker variability, and environmental noise. This paper addresses this challenge by investigating Speech Emotion Recognition (SER) using a combination of handcrafted audio features and machine learning and deep learning models. We extract Mel-Frequency Cepstral Coefficients (MFCCs), chroma, spectral contrast, and energy-based descriptors from preprocessed speech signals, aggregated into fixed-length vectors for classical classifiers such as Support Vector Machines (SVM) and Multilayer Perceptrons (MLP). For deep learning, sequential and spatial representations are captured using Long Short-Term Memory (LSTM) networks and 2D Convolutional Neural Networks (CNNs) trained on log-mel spectrograms. Experiments on the Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) and additional benchmark corpora show that the spectrogram-based 2D CNN achieves the highest accuracy of 82.3% on a seven-class task where calm and neutral emotions are merged. The results demonstrate the importance of robust feature representation and lightweight neural architectures for reliable SER, and we provide reproducible protocols to facilitate future research.
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 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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; 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".