-
Southeast University, Nanjing, China
- Shanghai, China
-
08:21
(UTC +08:00) - https://pecholal.github.io/
- https://orcid.org/0009-0000-9103-5783
- https://scholar.google.com/citations?user=rP_RLDcAAAAJ
Lists (7)
Sort Name ascending (A-Z)
Fingerprinting&Signature
Fingerprinting::Deepfake Rooting::User AttributionSpeech Security
speaker verification, speaker anonymizationVoice Converion
Voice ConversionWatermarking
Neural Watermarking搵食
DL都係浮雲,做工時間做工有趣
好耍歪綺麗なINN
きれいな invertible neural networkStars
Source Code for ECAI 2024 Paper "Leveraging Foundation Models for Zero-Shot IoT Sensing"
This is a fun, new monospaced font that includes programming ligatures and is designed to enhance the modern look and feel of the Windows Terminal.
An open-source Chinese font derived from Fontworks' Klee One. 一款开源中文字体,基于 FONTWORKS 出品字体 Klee One 衍生。
Official implementation of the paper "The Stable Signature Rooting Watermarks in Latent Diffusion Models"
📄 Awesome CV is LaTeX template for your outstanding job application
WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Models (CVPR 2024)
The official PyTorch implementation for ICCV'21 Oral paper 'Artificial GAN Fingerprints: Rooting Deepfake Attribution in Training Data'
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
Unofficial reimplementation of ECAPA-TDNN for speaker recognition (EER=0.86 for Vox1_O when train only in Vox2)
Concise, consistent, and legible badges in SVG and raster format
Spring Boot Tutorial takes you to learn Spring Boot step by step with a large number of samples.Spring Boot Tutorial 是一本关于 Spring Boot 学习的开源书。用大量实例带你一步一步走进 Spring Boot 的世界。
Lightweight Speech Representation Learning for One-Shot Voice Conversion
Deep Speaker: an End-to-End Neural Speaker Embedding System.
Code for the paper "Guided Image Generation with Conditional Invertible Neural Networks" (2019)
VoicePAT is a modular and efficient toolkit for voice privacy research, with main focus on speaker anonymization.
自己的学习笔记。包含:个人秋招经历、🐂客面经问题按照频率总结、Java一系列知识、数据库、分布式、微服务、前端、技术面试、每日文章等(持续更新)
HyMPS will be a platform-indipendent software suite for advanced audio/video contents production.
Robust Neural Audio Watermarking with Invertible Dual-Embedding
Implementations of different audio watermarking techniques
Paper 'Towards Blind Watermarking: Combining Invertible and Non-invertible Mechanisms' in ACM Multimedia '22.
End-to-End Zero-Shot Voice Conversion with Location-Variable Convolutions