/Speech-Processing-course

This repo contains speech processing course exersices held in SRU by Dr. Mohammad Kalantari.

Primary LanguageJupyter Notebook

Speech Processing Course

This repo contains speech processing course exersices held in SRU with Dr. Mohammad Kalantari.

1. Voice (Isolated Numbers) Recognition System

System for voice processing and recognition, especially for isolated digits in English. Recognition is done with Gaussian Mixture Models – Hidden Markov Models and also a Recurrent Neural Network is implemented with Pytorch.
data is taken from : link.

2. Speech Production

This is a simple python code to reproduce my name's speech signal.