Combined Acoustic Features with CNN-BiLSTM-Transformer for Female Emotion Recognition
Bibliographic record
Abstract
Speech Emotion Recognition (SER) is essential for enhancing human-computer interaction by enabling machines to understand user emotional states.However, SER still faces challenges, such as the complexity of audio signals, individual differences, and limited focus on female voices, which often exhibit higher pitch and subtler emotional cues.This study introduces a hybrid model combining Convolutional Neural Network (CNN), Bidirectional Long Short-Term Memory (BiLSTM), and Transformer to classify emotions in female speech.The model is trained using the RAVDESS, CREMA-D, and TESS datasets, with stepwise acoustic features: MFCC, ZCR, LPC, RMSE, and ZCPA.Data augmentation techniques are applied to address class imbalance and improve generalization, including the addition of additive noise and pitch shifting to simulate natural variations in female vocal pitch.Additionally, SMOTE is employed to generate synthetic samples for minority classes.Performance is evaluated using 5-fold cross-validation.Results show that the best performance is achieved using the MFCC + ZCR combination, with 88.52% accuracy, 88.80% precision, 88.52% recall, 88.53% F1-score, and 98.95% AUC-ROC.This research advances SER by developing a robust, context-aware model tailored to female vocal traits.
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) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".