A tutorial for Speech Enhancement researchers and practitioners. The purpose of this repo is to organize the world’s resources for speech enhancement and make them universally accessible and useful.

This repo summarizes the tutorials, datasets, papers, codes and tools for speech separation and speaker extraction task. You are kindly invited to pull requests.

Deep neural network based speech enhancement toolkit

Spectral Subtraction, Wiener Filtering, MMSE

Glottal Flow Model-based Iterative Adaptive Inverse Filtering

Objective measures of speech quality SNR

Real time monitoring of highways

Voice Activity Detection in speech signals using short time energy and zero-crossings rate

Functions for creating speech features in MATLAB.

Maltab code for extraction of Mel Frequency Cepstral Coefficients

This repository is developed in MATLAB. Speech Augmentation is based on Adaptive Filtering while Endpoint Detection is based on Voice Activity Detection(VAD)

robust voice activity detection (VAD) algorithm for mono/stereo channels

Mel Frequency Cepstral Coefficients (MFCCs) are a feature widely used in automatic speech and speaker recognition. They were introduced by Davis and Mermelstein in the 1980s, and have been state-of-the-art ever since. In this project, we have implemented MFCC feature extraction in Matlab.

Using CIS (Continuous Interleaved Sampling) strategy of cochlear implant to process the audio YannyLaurel

Solutions to the exercise class for Speech Signal Processing course in University of Hamburg

A simple text-dependent speaker-recognition system in two different approaches: LPC averaging and MFCC

Speech Processing - Detect voiced and unvoiced speech

Voice gender detection by octave

Compare graphs of detected Fundamental Frequency contours: Praat vs MATLAB. Used Cepstrum in MATLAB to detect Fundamental Frequency (Pitch) in speech.