speech-processing

A PyTorch-based Speech Toolkit

Reading list for research topics in multimodal machine learning

WaveNet vocoder

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

SincNet is a neural architecture for efficiently processing raw audio samples.

A curated list of awesome Speaker Diarization papers, libraries, datasets, and other resources.

A neural network for end-to-end speech denoising

Speech recognition toolkit for the arduino

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.

Problem Agnostic Speech Encoder

Novoic's audio feature extraction library

Library to build speech synthesis systems designed for easy and fast prototyping.

A python wrapper for Speech Signal Processing Toolkit (SPTK).

This repository has implementation for "Neural Voice Cloning With Few Samples"

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.

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

Speech Algorithms Collections

Real-time GCC-NMF Blind Speech Separation and Enhancement

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

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

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

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

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

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

Deep neural network based speech enhancement toolkit

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].

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