Deep dive into Claude Code internals — architecture, agent loop, context engineering, and more. / 深入解析 Claude Code 源码：架构、Agent 循环、上下文工程、工具系统等

Official implementation of VING: Variational Bayesian Inference with Neural Guidance for Speech Dereverberation

This is the official implementation of the SEMamba paper. (Accepted to IEEE SLT 2024)

EDM2SE: A Magnitude-Preserving Network Architecture for Diffusion-Based Speech Enhancement

Zhejiang University Graduation Thesis LaTeX Template

Exploring Unsupervised Cell Recognition with Prior Self-activation Maps (MICCAI 2023)

Official PyTorch implementation of 'Rec-RIR: Monaural Blind Room Impulse Response Identification via DNN-based Reverberant Speech Reconstruction in STFT Domain'

This is the official implementation of reverberant speech to room impulse response estimator

This is the official implementation of our neural-network-based fast diffuse room impulse response generator (FAST-RIR) for generating room impulse responses (RIRs) for a given acoustic environment.

Translating Synthetic RIRs to Real RIRs

NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment

Diffusion models for speech quality assessment

This is an open-source implementation of the ITU P.808 standard for "Subjective evaluation of speech quality with a crowdsourcing approach" (see https://www.itu.int/rec/T-REC-P.808/en). It uses Ama…

Easiest solution for online MOS metric evaluation

Unofficial Pytorch Implementation for Neural Network Room Impulse Estimation from Speech

Implementation of FiNS model for RIR estimation

The Official PyTorch Implementation of "Mel-McNet: A Mel-Scale Framework for Online Multichannel Speech Enhancement" [Interspeech 2025]

AI机器人群聊

Pytorch implementation of "CleanMel: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR".

AcadHomepage: A Modern and Responsive Academic Personal Homepage

Homepage

Official PyTorch implementation of 'VINP: Variational Bayesian Inference with Neural Speech Prior for Joint ASR-Effective Speech Dereverberation and Blind RIR Identification' [IEEE TASLP]

End-to-End Speech Processing Toolkit

Implementation of journal paper entitled 'An off-grid wideband DOA estimation method with the variational Bayes expectation-maximization framework' for DOA estimation [Signal Processing]

Implementation of journal paper entitled '1-Bit direction of arrival estimation via improved complex-valued binary iterative hard thresholding' for DOA estimation [Digital Signal Processing]

On the Variance of the Adaptive Learning Rate and Beyond

BUDDy: Single-Channel Blind Unsupervised Dereverberation with Diffusion Models