Bridging the Emotional Gap in AI: A Study on Speech Emotion Recognition for Adaptive Human Computer Interaction
Bibliographic record
Abstract
Speech Emotion Recognition (SER) is an advancement that has attracted a lot of interest because of its potential uses in intelligent systems, mental health monitoring, and human-computer interaction (HCI). Even with the progress made in AI-driven HCI, many systems are still unable to accurately sense and comprehend human emotions. Virtual assistants may carry out tasks based on spoken instructions, but they don't react well to user’s emotions, which results in less-than-ideal interactions. In order to close this gap, this study implements a speech emotion recognition algorithm that uses the Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS), and Toronto Emotional Speech Set (TESS) datasets to examine voice characteristics. The system makes use of cutting-edge deep learning methods including Long Short-Term Memory (LSTM) networks to capture temporal relationships in speech patterns and Convolutional Neural Networks (CNNs) for feature extraction from spectrograms which results in building a Hybrid Model. Traditional machine learning models may not be able to capture subtle emotional nuances in complex data, but they do offer faster processing times and easier implementations. Conversely, deep learning models, including 2D architecture such as CNNs and LSTMs, need more processing power but are better at handling large datasets and detecting subtle emotional cues. By leveraging these advancements, this research aims to enhance virtual assistants and similar systems to better recognize and respond to emotional cues in real time. Thus, Opening the door for a technological environment that is more user-centered and sympathetic.
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 | 0.005 |
| 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 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
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".