Analisis Perbandingan Optimasi Stochastic Gradient Descent dan Adaptive Moment Estimation dalam Klasifikasi Emosi dari Audio Menggunakan Convolutional Neural Network
Bibliographic record
Abstract
Emotion plays a fundamental role in human life, influencing behavior, social interaction, anddecision-making. Successful communication and understanding between individuals depend greatly on ourability to recognize and express emotions. In this context, sound or audio plays a key role as a medium thatreflects and conveys human emotional expression. In the era of information technology and artificialintelligence, emotion recognition through sound has become a growing focus of research. Machine learningalgorithms, particularly neural networks, can be trained to understand and classify emotions conveyed invarious forms, including text, images, videos, and audio. Among these algorithms, Convolutional NeuralNetwork (CNN) has shown promising performance in emotion classification tasks. In this study, thecomparison between Stochastic Gradient Descent (SGD) and Adaptive Moment Estimation (Adam)optimizers in emotion classification from audio using CNN is investigated. The research aims to determinethe optimal optimizer for emotion classification tasks. The results suggest that SGD optimizer outperformsAdam in terms of overall accuracy, with SGD achieving 53% accuracy compared to Adam's 48% accuracy inThe Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) dataset. Therefore, foremotion classification from audio data, Stochastic Gradient Descent (SGD) optimizer is recommended forbetter performance.
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 | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 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".