Speech enhancement using Wiener filtering and pitch-synchronous STFT phase reconstruction

The MOS system combines components from DNSMOS, NISQA, MOSSSL, and SIGMOS, using the librosa library to process audio waveforms.

Denoising Diffusion Probabilistic Models

Score-based Generative Models (Diffusion Models) for Speech Enhancement and Dereverberation

DiffWave is a fast, high-quality neural vocoder and waveform synthesizer.

State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz mono/stereo audio.

Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audi…

A PyTorch-based Speech Toolkit

An Open-source Streaming High-fidelity Neural Audio Codec

Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audi…

Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audi…

FunCodec is a research-oriented toolkit for audio quantization and downstream applications, such as text-to-speech synthesis, music generation et.al.

High-Resolution Image Synthesis with Latent Diffusion Models

A latent text-to-image diffusion model

Audio generation using diffusion models, in PyTorch.

A fully working pytorch implementation of NaturalSpeech (Tan et al., 2022)

Implementation of Natural Speech 2, Zero-shot Speech and Singing Synthesizer, in Pytorch

iSTFTNet : Fast and Lightweight Mel-spectrogram Vocoder Incorporating Inverse Short-time Fourier Transform

Source code for "Taming Visually Guided Sound Generation" (Oral at the BMVC 2021)

On Variational Learning of Controllable Representations for Text without Supervision https://arxiv.org/abs/1905.11975

Audio Generation model working with GPT-2 and VQVAE compressed representation of MelSpectrograms

VQVAE compression for MelSpectrograms

Automatic Speaker Recognition (ASR) system using Mel Frequency Cepstral Coefficients (MFCC's) and Vector Quantization (VQ)

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 em…

Implementation of "MOSNet: Deep Learning based Objective Assessment for Voice Conversion"