Skip to content

Latest commit

 

History

History
11 lines (6 loc) · 652 Bytes

README.md

File metadata and controls

11 lines (6 loc) · 652 Bytes

Audio Classification of Emotional Inputs

My master's thesis at Columbia University explores the intersection of speech language processing and journalism: How can speech or audio analysis be used to further a written piece?

In order to partly answer this question, I utilized pyAudioAnalysis to build a classifier that would categorize short utterances into one of five emotional categories: anger, disgust, fear, happiness, and sadness.

The training data that I used for classifier came from the CREMA-D.

Project by: Navraj Narula