[ICASSP 2024] This is the official code for "VoiceFlow: Efficient Text-to-Speech with Rectified Flow Matching"

🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching

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

Diff-TTSG: Denoising probabilistic integrated speech and gesture synthesis

TorchCFM: a Conditional Flow Matching library

pytorch implementation of openai paper "Glow: Generative Flow with Invertible 1×1 Convolutions"

GENEA Challenge visualiser running in local

Scripts for numerical evaluations for the GENEA Gesture Generation Challenge

Putting flows on top of neural transducers for better TTS

Code to reproduce the results for our SIGGRAPH 2023 paper "Listen Denoise Action"

YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone

A curated list of resources for natural language processing (NLP) in Swedish

A collator for speech datasets with different batching strategies and attribute extraction.

This is the official repository for our publication "The IVI Lab entry to the GENEA Challenge 2022 – A Tacotron2 Based Method for Co-Speech Gesture Generation With Locality-Constraint Attention Mec…

ZeroEGGS: Zero-Shot Example-Based Gesture Generation from Speech

This is the official implementation for IVA '19 paper "Analyzing Input and Output Representations for Speech-Driven Gesture Generation".

This repository contains data pre-processing and visualization scripts used in GENEA Challenge 2022 and 2023. Check the repository's README.md file for instructions on how to use scripts yourself.

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Data manipulation and transformation for audio signal processing, powered by PyTorch

A suite of speech signal processing tools

Neural HMMs are all you need (for high-quality attention-free TTS)

Code for paper "Integrated Speech and Gesture Synthesis"(ICMI 2021)

This repository is an attempt to document PER results on TIMIT for personal literature survey purposes

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

A Flow-based Generative Network for Speech Synthesis