Implementasi Algoritma Deep Artificial Neural Network Menggunakan Mel Frequency Cepstrum Coefficient Untuk Klasifikasi Audio Emosi Manusia
Bibliographic record
Abstract
Emosi merupakan keadaan yang dirasakan pada setiap individu dalam intensitas yang tinggi terhadap sesuatu hal. Emosi sulit dipahami dan sulit diukur secara kuantitatif. Emosi dapat tercermin dalam ekspresi wajah dan nada suara. Suara mengandung sifat fisik yang unik untuk setiap pembicara. Setiap orang memiliki warna nada, tempo, dan ritme yang berbeda. Oleh karena itu, Identifikasi emosi manusia berguna dalam bidang interaksi manusia dan komputer. Ini membantu mengembangkan antarmuka perangkat lunak yang dapat diterapkan di pusat layanan masyarakat, bank, pendidikan, dan lainnya. Pada penelitian ini, digunakan model berbasis Deep Artificial Neural Network (Deep ANN) dalam mengklasifikasikan emosi suara. Dataset yang digunakan ialah “Toronto Emotional Speech Set” dengan 14 class dan 2.800 data audio. Deep ANN tersusun dari 2 hidden layer dengan masing-masin 100 dan 7 neuron menggunakan fungsi aktivasi Rectified Linear Unit (ReLU). Ekstraksi fitur diberlakukan untuk semua file audio menggunakan metode Mel Frequency Cepstrum Coefficient (MFCC). Berdasarkan hasil yang diperoleh, arsitektur berbasis Deep ANN ini dengan 100 epoch mendapatkan tingkat akurasi yang sangat baik dengan nilai akurasi adalah 99.71%, presisi rata-rata 99.97%, recall rata-rata 99.97%, dan skor F1 rata-rata 99.97%.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 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 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 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".