Lists (2)
Stars
Deep neural networks for voice conversion (voice style transfer) in Tensorflow
Singing Voice Conversion via diffusion model
Implementations of audio watermarking methods, speech quality metrics and attacks in different domains.
Parallel data voice conversion based on pix2pix
Audio Deepfake Classification on ASVSpoof 2019 LA Dataset.
Streamlit application for generating and detecting deepfakes. Generates deepfakes in audio, image, and video, and detects deepfakes in images. Uses advanced AI models for accurate results.
This project focuses on detecting deepfake audio using advanced neural network architectures like VGG16, MobileNet, ResNet, and custom CNNs. It incorporates explainable AI (XAI) methods like LIME, …
[ACM MM Award] AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset
An audio deepfake is when a “cloned” voice that is potentially indistinguishable from the real person’s is used to produce synthetic audio.
Contains colab files for making audio and video with deep fakes
The Microsoft Scalable Noisy Speech Dataset (MS-SNSD) is a noisy speech dataset that can scale to arbitrary sizes depending on the number of speakers, noise types, and Speech to Noise Ratio (SNR) l…
NPTEL2020: Speech2Text dataset for Indian-English Accent
Codes to reproduce the Inner speech Dataset publicated by Nieto et al.
CSS10: A Collection of Single Speaker Speech Datasets for 10 Languages
Digital audio watermarker that can encode and extract secret messages from sound files. Written using MATLAB as well as implemented a python model.
A python tool to identify different Hash Function Algorithms
The Mersenne Twister pseudo-random number generator implemented in Python
Website & Documentation: https://sbaresearch.github.io/model-watermarking/
Watermarking against model extraction attacks in MLaaS. ACM MM 2021.
Code of the paper: A Recipe for Watermarking Diffusion Models