Tacotron 2 - PyTorch implementation with faster-than-realtime inference

Robust Speech Recognition via Large-Scale Weak Supervision

语音识别理论、论文和PPT

A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统

Foundational Models for State-of-the-Art Speech and Text Translation

Tracking the progress in end-to-end speech translation

List of direct speech-to-speech translation papers.

vits2 backbone with multilingual-bert

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

Reference BLEU implementation that auto-downloads test sets and reports a version string to facilitate cross-lab comparisons

PyTorch Implementation of TranSpeech (ICLR'23): Textless NAR Speech-to-Speech Translation with Bilateral Perturbation

StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.

🌏 Review notes for Postgraduate Interview of Tsinghua EE. (Sept. 2017)

State-of-the-art deep learning based audio codec supporting both mono 24 kHz audio and stereo 48 kHz audio.

Efficient neural speech synthesis

Recurrent neural network for audio noise reduction

Conformer-based Metric GAN for speech enhancement

Implementation of paper "DPCRN: Dual-Path Convolution Recurrent Network for Single Channel Speech Enhancement"

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

Real Time Speech Enhancement in the Waveform Domain (Interspeech 2020)We provide a PyTorch implementation of the paper Real Time Speech Enhancement in the Waveform Domain. In which, we present a ca…

Noise supression using deep filtering

speech enhancement\speech seperation\sound source localization

Deep learning for audio denoising

A Very Low-Bitrate Codec for Speech Compression

💎 A list of accessible speech corpora for ASR, TTS, and other Speech Technologies

Chinese voice corpus. 中文语音语料，语音更加清晰自然，包含8个开源数据集，3200个说话人，900小时语音，1300万字。

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.