This project presents a deep learning classifier able to predict the emotions of a human speaker encoded in an audio file. The classifier is trained using 2 different datasets, RAVDESS and TESS on 8 classes (neutral, calm, happy, sad, angry, fearful, disgust and surprised).
For this task, the dataset is built using 5252 samples from:
-
1440 speech files and 1012 Song files from RAVDESS. This dataset includes recordings of 24 professional actors (12 female, 12 male), vocalizing two lexically-matched statements in a neutral North American accent. Speech includes calm, happy, sad, angry, fearful, surprise, and disgust expressions, and song contains calm, happy, sad, angry, and fearful emotions. Each file was rated 10 times on emotional validity, intensity, and genuineness. Ratings were provided by 247 individuals who were characteristic of untrained adult research participants from North America. A further set of 72 participants provided test-retest data. High levels of emotional validity, interrater reliability, and test-retest intrarater reliability were reported. Validation data is open-access, and can be downloaded along with our paper from PLoS ONE.
-
2800 files from TESS. A set of 200 target words were spoken in the carrier phrase "Say the word _____' by two actresses (aged 26 and 64 years) and recordings were made of the set portraying each of seven emotions (anger, disgust, fear, happiness, pleasant surprise, sadness, and neutral). There are 2800 stimuli in total. Two actresses were recruited from the Toronto area. Both actresses speak English as their first language, are university educated, and have musical training. Audiometric testing indicated that both actresses have thresholds within the normal range.
The classes the model wants to predict are the following: (0 = neutral, 1 = calm, 2 = happy, 3 = sad, 4 = angry, 5 = fearful, 6 = disgust, 7 = surprised).
Each of the 7356 RAVDESS files has a unique filename. The filename consists of a 7-part numerical identifier (e.g., 02-01-06-01-02-01-12.wav). These identifiers define the stimulus characteristics:
Filename identifiers
- Modality (01 = full-AV, 02 = video-only, 03 = audio-only).
- Vocal channel (01 = speech, 02 = song).
- Emotion (01 = neutral, 02 = calm, 03 = happy, 04 = sad, 05 = angry, 06 = fearful, 07 = disgust, 08 = surprised).
- Emotional intensity (01 = normal, 02 = strong). NOTE: There is no strong intensity for the ‘neutral’ emotion.
- Statement (01 = “Kids are talking by the door”, 02 = “Dogs are sitting by the door”).
- Repetition (01 = 1st repetition, 02 = 2nd repetition).
- Actor (01 to 24. Odd numbered actors are male, even numbered actors are female).
Filename example: 02-01-06-01-02-01-12.wav
- Video-only (02)
- Speech (01)
- Fearful (06)
- Normal intensity (01)
- Statement “dogs” (02)
- 1st Repetition (01)
- 12th Actor (12)
- Female, as the actor ID number is even.