Multimodal Emotion Recognition with Fusion of 1D and 2D Convolutional Neural Network
Bibliographic record
Abstract
Emotion is one of the key components in daily life, serving multiple purposes in social interactions. The advancements in Artificial Intelligence (AI) had made emotion recognition possible with more accurateness. The AI model, specifically the Convolutional Neural Network (CNN), had presented superior performance in computer vision and image recognition tasks, leading to highly accurate Emotion Recognition (ER). However, the typical CNN architecture is mostly complex and hardly adaptable for real-time applications, especially when multi-input types are involved. To overcome this challenge, this study proposes a tailored lightweight Multimodal Emotion Recognition CNN architecture that accepts facial images and vocal features (i.e., mel-spectrogram in decibels) as input and is benchmarked on Surrey Audio-Visual Expressed Emotion (SAVEE) and Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS). The SAVEE dataset contains recordings of 4 male actors with single level emotion intensity while RAVDESS contains recordings of 24 actors, balanced in gender, with two levels of emotion intensity. The lightweight CNN model achieved an on-par accuracy of 97.15% in SAVEE and 86.72% in RAVDESS while significantly simpler than state-of-the-arts MER models, making it a more feasible option for real-time emotion recognition on resource-constrained devices.
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 | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".