Overview / Usage

Voicenet is a comprehensive library for performing speech/voice based functions. It is capable of doing:

• Speechtotext (STT)
• Geneder detection based on the voice.
• Pronunciation posterior score
• Articulation-rate
• Speech rate
• Filler words
• Age detection from voice.
• Emotion detection from voice.
• Neural voice transfer (NVT)

Methodology / Approach

Using Fast Fourier Transforms and Mel-frequency cepstral coefficients (MFCCs) to generate features and training Gaussian Mixture Models (GMM) to do the required tasks

Technologies Used

Python

Numpy

Pandas

Sklearn

Repository

https://pypi.org/project/voicenet/

Other links

• Github (https://github.com/Robofied/Voicenet)