Stars
Code for paper "Audio Deepfake Detection with Self-supervised XLS-R and SLS classifier
This is the official repo of our work titled "The Codecfake Dataset and Countermeasures for the Universally Detection of Deepfake Audio".
A list of tools, papers and code related to Deepfake Detection.
[ACM CCS'24] SafeEar: Content Privacy-Preserving Audio Deepfake Detection
Research progress on speech deepfake detection: Relevant datasets aggregated from the review literature and publicly available codes
List of papers that combine self-supervision and continual learning
UniCodec: a unified audio codec with a single codebook to support multi-domain audio data, including speech, music, and sound
SlamKit is an open source tool kit for E8F2 efficient training of SpeechLMs. It was used for "Slamming: Training a Speech Language Model on One GPU in a Day"
[CVPR 2025] MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis
Welcome to AudioCIL, the toolbox for audio class-incremental learning with the most implemented methods.
A tool to collect/validate audio recordings from workers on Amazon Mechanical Turk. Written in Python/Flask. (originally hosted on github.mit.edu)
VoiceBench: Benchmarking LLM-Based Voice Assistants
Code for paper: IDEA: Increasing Text Diversity via Online Multi-Label Recognition for Vision-Language Pre-training [ACM MM2022]
Awesome Incremental Learning
This repo will be continually updating analytic federated learning methods.
This is the official code for the paper "Reconstruct before Query: Continual Missing Modality Learning with Decomposed Prompt Collaboration."
🎉 PILOT: A Pre-trained Model-Based Continual Learning Toolbox
The official PyTorch code for ICLR'22 Paper "Learning Fast, Learning Slow: A General Continual Learning Method based on Complementary Learning System""
This repository will be posting analytic continual learning series, including Analytic Class-Incremental Learning (ACIL), Gaussian Kernel Embedded Analytic Learning (GKEAL), Dual-Stream Analytic Le…
Mixing an audio file with a noise file at any Signal-to-Noise Ratio (SNR)
PyTorch implementation of VQ-VAE + WaveNet by [Chorowski et al., 2019] and VQ-VAE on speech signals by [van den Oord et al., 2017]
Pytorch port of Google Research's VGGish model used for extracting audio features.