# Speech-Backbones

**Repository Path**: mirrors_huawei-noah/Speech-Backbones

## Basic Information

- **Project Name**: Speech-Backbones
- **Description**: This is the main repository of open-sourced speech technology by Huawei Noah's Ark Lab.
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2021-07-20
- **Last Updated**: 2026-03-29

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# Speech-Backbones

This is the main repository of open-sourced speech technology by Huawei Noah's Ark Lab.

## Grad-TTS

Official implementation of the Grad-TTS model based on Diffusion Probabilistic Modelling. For all details check out our paper accepted to ICML 2021 via [this](https://arxiv.org/abs/2105.06337) link.

 **Authors**: Vadim Popov\*, Ivan Vovk\*, Vladimir Gogoryan, Tasnima Sadekova, Mikhail Kudinov.

 <sup>\*Equal contribution.</sup>
 
## SPIRAL
 
Official implementation of SPIRAL: Self-supervised Perturbation-Invariant Representation Learning for Speech Pre-Training. For all details check out our paper accepted to ICLR 2022 via [this](https://arxiv.org/abs/2201.10207) link.

**Authors**: Wenyong Huang, Zhenhe Zhang, Yu Ting Yeung, Xin Jiang, Qun Liu.
 
## DiffVC

Official implementation of the paper "Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme" (ICLR 2022, Oral). [Link](https://arxiv.org/abs/2109.13821).

**Authors**: Vadim Popov, Ivan Vovk, Vladimir Gogoryan, Tasnima Sadekova, Mikhail Kudinov, Jiansheng Wei.