AcademiCodec: An Open Source Audio Codec Model for Academic Research

Code for paper "Noise-aware Speech Enhancement using Diffusion Probabilistic Model"

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

Official repository for the "Powerset multi-class cross entropy loss for neural speaker diarization" paper published in Interspeech 2023.

深度学习经典、新论文逐段精读

强化学习中文教程（蘑菇书🍄），在线阅读地址：https://datawhalechina.github.io/easy-rl/

[TPAMI 2024 & CVPR 2023] PyTorch code for DGM4: Detecting and Grounding Multi-Modal Media Manipulation and beyond

Variational Bayes HMM over x-vectors diarization

AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head

ADAPTING SELF-SUPERVISED MODELS TO MULTI-TALKER SPEECH RECOGNITION USING SPEAKER EMBEDDINGS

Python toolkit for speech processing

A torch implementation of a recursion which turns out to be useful for RNN-T.

Robust Speech Recognition via Large-Scale Weak Supervision

A curated list of awesome Speech Enhancement papers, libraries, datasets, and other resources.

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

A PyTorch-based Speech Toolkit

This repo contains my attempt to create a Speaker Recognition and Verification system using SideKit-1.3.1

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

Source code for: Efficient Self-supervised Learning Representations for Spoken Language Identification

[NeurIPS 2023] Unsupervised Video Domain Adaptation for Action Recognition: A Disentanglement Perspective

Final project for the Speaker Recognition course on Udemy, 机器之心, 深蓝学院 and 语音之家

LeetCode Solutions: A Record of My Problem Solving Journey.( leetcode题解，记录自己的leetcode解题之路。)

PHO-LID: A Unified Model to Incorporate Acoustic-Phonetic and Phonotactic Information for Language Identification

End-to-End Speech Processing Toolkit