从零手搓Flow Matching（Rectified Flow）

The Microsoft Scalable Noisy Speech Dataset (MS-SNSD) is a noisy speech dataset that can scale to arbitrary sizes depending on the number of speakers, noise types, and Speech to Noise Ratio (SNR) l…

PyTorch implementation of Glow

Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model

[ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching

Command line utility for forced alignment using Kaldi

Audio Codec Benchmark

Fake speech detection with the CodecFake dataset

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

A list of tools, papers and code related to Fake Audio Detection.

Fake Lossless Audio Detector

This project uses a variety of advanced voiceprint recognition models such as EcapaTdnn, ResNetSE, ERes2Net, CAM++, etc. It is not excluded that more models will be supported in the future. At the …

Implementation of the paper "Improved DeepFake Detection Using Whisper Features"

This repository includes the code to reproduce our paper "End-to-End Spectro-Temporal Graph Attention Networks for Speaker Verification Anti-Spoofing and Speech Deepfake Detection" (https://arxiv.o…

Research progress on speech deepfake detection: Relevant datasets aggregated from the review literature and publicly available codes

[InterSpeech'2023] "Betray Oneself: A Novel Audio DeepFake Detection Model via Mono-to-Stereo Conversion"

pytorch structural similarity (SSIM) loss

Vector Quantized VAEs - PyTorch Implementation

Vector (and Scalar) Quantization, in Pytorch

Brand new TTS solution

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

singing voice change based on whisper, and lora for singing voice clone

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

Implementation of SoundStorm, Efficient Parallel Audio Generation from Google Deepmind, in Pytorch

KAN-TTS is a speech-synthesis training framework, please try the demos we have posted at https://modelscope.cn/models?page=1&tasks=text-to-speech

Speech Recognition using DeepSpeech2.

List of speech synthesis papers.