HERF: A Machine Learning Framework for Automatic Emotion Recognition from Audio
Bibliographic record
Abstract
Human emotion recognition from audio has potential applications such as healthcare, feedback assessment, gaming and advertisement to mention few.Human emotion detection often helps in assessing the feelings of person automatically.It could lead to making well informed decisions.Advancements in machine learning (ML) has paved way for unprecedented possibilities in emotion recognition from audio automatically.The methods identified in existing literature exhibit limitations, notably the absence of feature engineering to enhance predictive performance.A framework is proposed based on ML for automatic recognition of human emotions from a given voice content.The framework is called the Human Emotion Recognition Framework (HERF), designed to receive audio datasets as input and employs supervised learning for the automated identification of human emotions based on audio signals.We proposed two algorithms for realizing the framework.A Hybrid Feature Selection (HFS) algorithm is introduced to enhance the efficiency of identifying features that could have discriminative power.Additionally, the Neural Network-based Automatic Emotion Recognition (NN-AER) algorithm, utilizing Multilayer Perceptron (MLP) and HFS, is proposed for automatic emotion recognition.The feature selection provided by the HFS algorithm improves the training quality of NN-AER.RAVDESS is dataset used for empirical study.This dataset supports emotions such as neutral, happy, sad, disgust, angry, fearful and surprised.We designed a web application used to recognise emotion for given audio sample based on saved MLP model.Results of our study revealed that NN-AER outperforms many states of the art methods.
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 | 0.002 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.007 | 0.003 |
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".