Voice Activity Detector (VAD) : low-latency, high-performance and lightweight

You can find the speech algorithms you want here

Identify the emotion of multiple speakers in an Audio Segment

A modified version of Speech Signal Processing Toolkit (SPTK)

Emotion recognition by speech in android.

Praaline is an open-source system to manage, annotate, visualise and analyse spoken language corpora

A smartphone applications with Convolutional Neural Network Voice Activity Detector, Adaptive Noise Reduction and Dynamic Audio Range Compression

Real-time speech enhancement based on spectral subtraction

Implementation of Adaptive Noise Reduction and Background Noise Classification using External Microphones on iOS

Subband filtering with ADPCM

A real-time speech analysis/synthesis system

Implementation of [Librosa](https://github.com/librosa/librosa) like [STFT](https://en.wikipedia.org/wiki/Short-time_Fourier_transform) using [FFTW](https://www.fftw.org/)

Repository to collect and design models for speech processing include keyword spotting, asr, tts, speech sinal process.

Digits Recognition 0-9 Using Hidden Markov Model in in the Subject Speech Processing CS 566 IITG.

This repository reimplements several state-of-the-art (SOTA) architectures for Keyword Spotting (KWS) using different approaches, including TCN, CRNN, and CNN, with the PyTorch framework. The models include MDTC, EdgeCRNN and BC-ResNet

Project Playlist Developed in the Subject Speech Processing CS 566 IITG.

Speech Algorithms Collections

This is a command based version of a speech recognition project. It is able to detect a few pre recorded words. It can also add new words by any speaker. The GUI version of this project is present at https://github.com/therohanjaiswal/Yugi