DeepSeek 系列工作解读、扩展和复现。

MiniCPM-o 2.6: A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone

🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!

A python package to build AI-powered real-time audio applications

Python re-implementation of the (constrained) spectral clustering algorithms used in Google's speaker diarization papers.

收集大语言模型的学习路径和各种最佳实践

A Python toolkit for sound source separation.

Python Adaptive Signal Processing

语音增强领域的相关数据仿真工具和方法汇总--持续更新

刷算法全靠套路，认准 labuladong 就够了！English version supported! Crack LeetCode, not only how, but also why.

speex aec kalman filter

Unsupervised domain adaptation for conversational speech enhancement using RemixIT

Dual-Path Attention and Recurrent Network for speech separation

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

This is a mandarin version of speech separation dataset like WSJMix and LibriMix

A collective list of free APIs

spatial signal processing toolkit a.k.a beamforming toolkit 2.0 (BTK2.0)

Speex Echo Canceller Python Library

The Cone of Silence:

Implementation of the paper "SNR-Based Progressive Learning of Deep Neural Network for Speech Enhancement."

🎤 Microphone sound source localization by SRP-PHAT and others numerical methods.（基于SRP-PHAT的麦克风声源定位）

Tools for Speech Enhancement integrated with Kaldi

MADE: Masked Autoencoder for Distribution Estimation

AEC Challenge

Analyze, visualize, and process sound field data recorded by spherical microphone arrays.

A Implementation of SpecAugment with Tensorflow & Pytorch, introduced by Google Brain

Python implementation of the Multiple Hypothesis Tracking algorithm

A MATLAB implementation of CHiME4 baseline Beamformit

Speech Enhancement Generative Adversarial Network in TensorFlow

Speech Enhancement based on DNN (Spectral-Mapping, TF-Masking), DNN-NMF, NMF