Development of a model for detecting emotions using CNN and LSTM
Bibliographic record
Abstract
This paper presents the development of a real-time deep learning system for emotion recognition using both speech and facial inputs. For speech emotion recognition, three significant datasets: SAVEE, Toronto Emotion Speech Set (TESS), and CREMA-D were utilized, comprising over 75,000 samples that represent a spectrum of emotions: Anger, Sadness, Fear, Disgust, Calm, Happiness, Neutral, and Surprise, mapped to numerical labels from 1 to 8. The system identifies emotions from live speech inputs and pre-recorded audio files using a Long Short-Term Memory (LSTM) network, which is particularly effective for sequential data. The LSTM model, trained on the RAVDEES dataset (7,356 audio files), achieved a training accuracy of 83%. For facial emotion recognition, a Convolutional Neural Network (CNN) architecture was employed, using datasets such as FER2013, CK+, AffectNet, and JAFFE. FER2013 includes over 35,000 labeled images representing seven key emotions, while CK+ provides 593 video sequences for precise emotion classification. By integrating LSTM for speech and CNN for facial emotion recognition, the system shows robust capabilities in identifying and classifying emotions across modalities, enabling comprehensive real-time emotion recognition.
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 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".