The Munich Open-Source Large-Scale Multimedia Feature Extractor

Versatile audio super resolution (any -> 48kHz) with AudioSR.

Unofficial implementation of HiFi-GAN+ from the paper "Bandwidth Extension is All You Need" by Su, et al.

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

DOSE: Diffusion Dropout with Adaptive Prior for Speech Enhancement, Conference on Neural Information Processing Systems (NeurIPS), 2023

Official implementation of Cold-Diffusion for different transformations in pytorch.

General Speech Restoration

Towards High-Quality and Efficient Speech Bandwidth Extension with Parallel Amplitude and Phase Prediction

HiFTNet: A Fast High-Quality Neural Vocoder with Harmonic-plus-Noise Filter and Inverse Short Time Fourier Transform

Explicit Estimation of Magnitude and Phase Spectra in Parallel for High-Quality Speech Enhancement

网络出处：Interactive Speech and Noise Modeling for Speech Enhancement

[NeurIPS 2022] Denoising Diffusion Restoration Models -- Official Code Repository

Score-based Generative Models (Diffusion Models) for Speech Enhancement and Dereverberation

HiFi++: a Unified Framework for Neural Vocoding, Bandwidth Extension and Speech Enhancement

Bandwidth Extension of Historical Recordings using Generative Adversarial Networks

NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment

CJKfuzz is a Python library for supporting fuzzy matching chinese string.

Chapter-level domain event extraction method: Take the military domain as an example

A SEU Course Project in The Course - "Special Topics in Knowledge Engineering", I Responsible for the iteration of technical solutions; knowledge extraction and integration. With solid and unique p…

A Military Knowledge Graph Using Baidu Relation Extraction Baseline System

brain-inspired model for emotional concept

[InterSpeech'2023] "Betray Oneself: A Novel Audio DeepFake Detection Model via Mono-to-Stereo Conversion"