VOCAL TONE DATASET (SRI LANKAN)

This dataset addresses the challenge of limited vocal recordings available in secondary datasets, particularly those that predominantly feature foreign accents and contexts. To enhance the accuracy of our solution tailored for Sri Lankans, we employed primary data-gathering methods.

The dataset comprises vocal recordings from a sample population of youth. Participants were instructed to read three specific sentences designed to capture a range of vocal tones:

1. He drove his car on the river bank without having any lights.
2. I saw him in the restaurant having a chat with my friends.
3. She has returned to the apartment with her dog.

Each sentence was read in five different emotional tones, allowing for a nuanced exploration of vocal expression.

Recordings were conducted in a controlled environment with minimal background noise, utilizing a condenser microphone (sensitivity: -30dB ± 2dB, frequency range: 20Hz-16KHz, impedance: 2.2k Ohm, connector: 3.5mm). This meticulous setup ensures high-quality audio suitable for various applications in voice analysis and emotion detection.