128 Open source projects that are alternatives of or similar to awesome-speech-enhancement

Source code for the paper titled "Speech Denoising without Clean Training Data: a Noise2Noise Approach". Paper accepted at the INTERSPEECH 2021 conference. This paper tackles the problem of the heavy dependence of clean speech data required by deep learning based audio denoising methods by showing that it is possible to train deep speech denoisi…

UniSpeech - Large Scale Self-Supervised Learning for Speech

A wavelet audio denoiser done in python

A framework for quick testing and comparing multi-channel speech enhancement and separation methods, such as DSB, MVDR, LCMV, GEVD beamforming and ICA, FastICA, IVA, AuxIVA, OverIVA, ILRMA, FastMNMF.

A speech dereverberation algorithm, also called wpe

End-to-End Speech Processing Toolkit

A statistical model-based Speech Enhancement Using MMSE-STSA

A Conditional Generative Adverserial Network (cGAN) was adapted for the task of source de-noising of noisy voice auditory images. The base architecture is adapted from Pix2Pix.

In this work we propose two postprocessing approaches applying convolutional neural networks (CNNs) either in the time domain or the cepstral domain to enhance the coded speech without any modification of the codecs. The time domain approach follows an end-to-end fashion, while the cepstral domain approach uses analysis-synthesis with cepstral d…

Pytorch implementation of subband decomposition

💎 A list of accessible speech corpora for ASR, TTS, and other Speech Technologies

HiFi-GAN: High Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networks

Real-time GCC-NMF Blind Speech Separation and Enhancement

Real time monaural source separation base on fully convolutional neural network operates on Time-frequency domain.

PyTorch implementation of VQ-VAE + WaveNet by [Chorowski et al., 2019] and VQ-VAE on speech signals by [van den Oord et al., 2017]

Deep neural network based speech enhancement toolkit

ACLEW Diarization Virtual Machine

🧹 Formerly for binary classification with noisy labels. Replaced by cleanlab.

Front-end speech processing aims at extracting proper features from short- term segments of a speech utterance, known as frames. It is a pre-requisite step toward any pattern recognition problem employing speech or audio (e.g., music). Here, we are interesting in voice disorder classification. That is, to develop two-class classifiers, which can discriminate between utterances of a subject suffering from say vocal fold paralysis and utterances of a healthy subject.The mathematical modeling of the speech production system in humans suggests that an all-pole system function is justified [1-3]. As a consequence, linear prediction coefficients (LPCs) constitute a first choice for modeling the magnitute of the short-term spectrum of speech. LPC-derived cepstral coefficients are guaranteed to discriminate between the system (e.g., vocal tract) contribution and that of the excitation. Taking into account the characteristics of the human ear, the mel-frequency cepstral coefficients (MFCCs) emerged as descriptive features of the speech spectral envelope. Similarly to MFCCs, the perceptual linear prediction coefficients (PLPs) could also be derived. The aforementioned sort of speaking tradi- tional features will be tested against agnostic-features extracted by convolu- tive neural networks (CNNs) (e.g., auto-encoders) [4]. The pattern recognition step will be based on Gaussian Mixture Model based classifiers,K-nearest neighbor classifiers, Bayes classifiers, as well as Deep Neural Networks. The Massachussets Eye and Ear Infirmary Dataset (MEEI-Dataset) [5] will be exploited. At the application level, a library for feature extraction and classification in Python will be developed. Credible publicly available resources will be 1used toward achieving our goal, such as KALDI. Comparisons will be made against [6-8].

Tensorflow 2.x implementation of the DTLN real time speech denoising model. With TF-lite, ONNX and real-time audio processing support.

Spokestack: give your React Native app a voice interface!

WaveNet vocoder

A minimum unofficial implementation of the "A Convolutional Recurrent Neural Network for Real-Time Speech Enhancement" (CRN) using PyTorch

MITK Diffusion - Official part of the Medical Imaging Interaction Toolkit

bLUe - A simple and comprehensive image editor featuring automatic contrast enhancement, color correction, 3D LUT creation, raw postprocessing, exposure fusion and noise reduction

PyTorch implementation of convolutional neural networks-based text-to-speech synthesis models

Tracking the progress in non-autoregressive generation (translation, transcription, etc.)

The SpeechBrain project aims to build a novel speech toolkit fully based on PyTorch. With SpeechBrain users can easily create speech processing systems, ranging from speech recognition (both HMM/DNN and end-to-end), speaker recognition, speech enhancement, speech separation, multi-microphone speech processing, and many others.

Implementation of Neural Voice Cloning with Few Samples Research Paper by Baidu

Pitch shifter using WSOLA and resampling implemented by Python3

A React-Native Bridge for the Google Dialogflow (API.AI) SDK

Neural Turing machine for source separation in Tensorflow

VocGAN: A High-Fidelity Real-time Vocoder with a Hierarchically-nested Adversarial Network

Deep CNN for learning image restoration without clean data!

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

multi-channel microphone array noise reduction

RETIRED - OpenSTT is now retired. If you would like more information on Mycroft AI's open source STT projects, please visit:

This repository is a curated list of awesome Speech Keyword Spotting (Wake-Up Word Detection).

Collection of EM algorithms for blind source separation of audio signals

Deep learning based Speech Beamforming

Rethinking Noise Synthesis and Modeling in Raw Denoising (ICCV2021)

Deep Learning-based Voice Conversion system

Neural speaker recognition/verification system based on Kaldi and Tensorflow

Implement Wave-U-Net by PyTorch, and migrate it to the speech enhancement.

A light weight neural speaker embeddings extraction based on Kaldi and PyTorch.

(ECCV 2020) Interactive Multi-Dimension Modulation with Dynamic Controllable Residual Learning for Image Restoration

Bob is a free signal-processing and machine learning toolbox originally developed by the Biometrics group at Idiap Research Institute, in Switzerland. - Mirrored from https://gitlab.idiap.ch/bob/bob

Emotion recognition by speech in android.

A modified version of Speech Signal Processing Toolkit (SPTK)

ConvNets for Audio Recognition using Google Commands Dataset

https://dodiku.github.io/audio_noise_clustering/results/ ==> An experiment with a variety of clustering (and clustering-like) techniques to reduce noise on an audio speech recording.

Pytorch implements Deep Clustering: Discriminative Embeddings For Segmentation And Separation

Aydin — User-friendly, Fast, Self-Supervised Image Denoising for All.

Discriminative Neural Clustering for Speaker Diarisation

PyTorch implementation of "A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement."

Discover, install, and share napari plugins

Keras (tensorflow) implementation of SincNet (Mirco Ravanelli, Yoshua Bengio - https://github.com/mravanelli/SincNet)

iOS application for finding formants in spoken sounds

🔉 spafe: Simplified Python Audio Features Extraction

Script to calculate SNR and SDR using python