Skip to content

Librosa is a Python library used for audio analysis. I used this library to detect the emotions of numerous audio clips of actors bundled together in a dataset('Ravedess dataset').

Notifications You must be signed in to change notification settings

ishan-agr/Speech-Emotion-Recognition-Using-Librosa

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 

Repository files navigation

This project aims to deliver a speech emotion recognition program using python's audio detection library Librosaa.
The project uses a dataset named "Ravedess", which contains numerous audio clips of various actors expressing different types of emotions 
such as "fear", "happy" ,"sad" etc.
Using Librosa, the emotion from the actor's speech is detected.
A histogram and a spectrogram have also been displayed for better analysis of the speeches.
Furthermore, we can use the NLP classifier module of python along with some others, to calculate the efficiency of predictions made by the program
for detecting emotions in the speeches.

About

Librosa is a Python library used for audio analysis. I used this library to detect the emotions of numerous audio clips of actors bundled together in a dataset('Ravedess dataset').

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published