Speech Emotion Recognition Using Deep Learning
Bibliographic record
Abstract
Speech is one of the primary forms of expression and is important for Emotion Recognition. Emotion Recognition is helpful to derive various useful insights about the thoughts of a person. Automatic speech emotion recognition is an active field of study in Artificial intelligence and Machine learning, which aims to generate machines that communicate with people via speech. In this work, deep learning algorithms such as Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) are explored to extract features and classify emotions such as calm, happy, fearful, disgust, angry, neutral, surprised and sad using the Toronto emotional speech set (TESS) dataset which consists of 2800 files. The features like Mel-frequency cepstral coefficients(MFCC), chroma and mel spectrogram are extracted from speech using the pre-trained networks such as Xception, VGG16, Resnet50, MobileNetV2, DenseNet121, NASNetLarge, EfficientNetB5, EfficientNetV2M, InceptionV3, ConvNeXtTiny, EfficientNetV2B2, EfficientNetB6, ResNet152V2. Features of the two different networks are fused using the fusion techniques such as Early, Mid, Late to get better optimum results. Features are then classified initially with the Long Short Term Memory (LSTM) finally resulted in the accuracy of 99%. In this paper the work is extended to RAVDESS dataset also which consists of seven emotions such as calm, joyful, sad, surprised, afraid, disgust and angry in total of 1440 files. Keywords: Convolution Neural Network, Recurrent Neural Network, speech emotion recognition, MFCC, Chroma, Mel, LSTM.
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 | 0.003 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".