Enhanced Emotion Recognition from Spoken Assamese Dialect: A Machine Learning Approach with Language-Independent Features
Bibliographic record
Abstract
This study explores the uncharted territory of automated emotion recognition in the Assamese language, a broadly spoken but under-researched dialect in Northeast India, using speech and signal processing techniques.Using a unique combination of languageindependent features, sophisticated supervised machine learning algorithms are employed to classify a spectrum of basic and derived emotions from spoken Assamese.An innovative fusion of non-personalized and personalized features is proposed for Speech Emotion Recognition (SER), wherein high-dimensional features are initially divided into subclasses using the Fuzzy C-means clustering algorithm.Subsequent implementation of multiple random forest classifiers facilitates the recognition and classification of emotions.Special attention is paid to certain emotions with overlapping transitions, which traditionally pose challenges to classification algorithms.Performance analysis is conducted using K-fold cross-validation, with the results validated against several key parameters and compared against baseline random forest algorithms.Remarkably, the proposed algorithm demonstrates superior performance, yielding an accuracy increase of approximately 4.26-4.50%compared to baseline models, suggesting effective classification without languagedependent features.Furthermore, this study contributes to the development of a practical application tool for SER.This tool holds potential utility for medical practitioners, enabling the accurate diagnosis of a patient's emotional state, thereby informing more effective treatment approaches.The implications of this research are vast, particularly for underexplored languages, and underline the importance of expanding emotion recognition studies to a wider linguistic landscape.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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; both teacher heads agree on what is shown here.
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".