Synergistic Fusion of Deep Learning Techniques for Holistic Analysis of Age Group, Gender and Emotion Prediction from Speech
Bibliographic record
Abstract
Voice-based recognition systems have garnered significant attention, owing to their versatile applications in domains such as human-computer interaction, virtual assistants, and affective computing. This research aims to address the challenges associated with concurrent processes and escalating latency in individual models by delving into the intricacies of simultaneous age-group, gender, and emotion recognition from speech data. To surmount these impediments, we present a comprehensive investigation employing three distinct modeling approaches: standalone models for age group, gender, and emotion recognition; sequential models wherein the output of one model serves as input for the next; and an integrated model proficient in concurrent detection of age-group, gender, and emotion. Drawing inspiration from video understanding techniques, the integrated model seeks to streamline recognition processes and minimize latency. Experimental datasets, including the Ryerson Audio-Visual Database of Emotional Speech (RAVDESS), Common voice dataset and Crowd-Sourced Emotional Actors Database (CREMA-D), are lever age-group for rigorous analysis. Evaluation metrics encompassing accuracy, latency, and memory usage-group are employed to compare the performance of the diverse models.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.002 | 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 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 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".