/Speaker-Accent-Recognition

Having many Audio Tracks and you want to know the accent of each track, How to do that?? This project aims to classify an Audio Track to a specific accent by using Mel-frequency cepstral coefficients (MFCCS) of Audio Track.

Primary LanguageJupyter Notebook

Speaker-Accent-Recognition

Having many Audio Tracks and you want to know the accent of each track, How to do that??

This project aims to classify an Audio Track to a specific accent by using Mel-frequency cepstral coefficients (MFCCS) of Audio Track.

Dataset Overview:

The dataset is provided by : UCI Machine Learning Repository

The dataset contains 329 rows and 13 columns.

The dataset has 12 attribute columns and 1 label column.

The 12 attribute columns obtained using MFCC on the original time domain soundtrack of the maximum 1s of reading of a word.

The label column contains the six possible accents considered {ES, FR, GE, IT, UK, US}.