Cocii

Music and Acoustic Engineering from Politecnico di Milano @polimi-ispl Currently working at Zhipu AI @THUDM Researching in Speech Synthesis.

Zhipu AiBeijing

Pinned Repositories

aasist
Official PyTorch implementation of "AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks"
Language:Python00
ACTaM-project
Project repository of the Advanced Coding Tools and Methodologies course.
Language:JavaScript0 0 00
bigvgan
Language:Python0 1 00
BirthDayofCqq
Language:JavaScript0 1 00
CMLS_HW1
Language:Jupyter Notebook0 1 00
CMLS_HW2_GROUP5
Language:C++0 1 00
CMLS_HW3_GROUP5
Language:Processing0 1 00
CMRM_project
Language:JavaScript00
CPAC_c
Language:Jupyter Notebook0 1 00
Grave-ity
Language:C#2 1 03

Cocii's Repositories

Cocii/Grave-ity
Language:C#2 1 03
Cocii/aasist
Official PyTorch implementation of "AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks"
Language:Python00
Cocii/ACTaM-project
Project repository of the Advanced Coding Tools and Methodologies course.
Language:JavaScript0 0 00
Cocii/bigvgan
Language:Python0 1 00
Cocii/BirthDayofCqq
Language:JavaScript0 1 00
Cocii/CMLS_HW1
Language:Jupyter Notebook0 1 00
Cocii/CMLS_HW2_GROUP5
Language:C++0 1 00
Cocii/CMLS_HW3_GROUP5
Language:Processing0 1 00
Cocii/CMRM_project
Language:JavaScript00
Cocii/CPAC_c
Language:Jupyter Notebook0 1 00
Cocii/Don-t_touch_white
Language:JavaScript1 0
Cocii/Enhanced-Text-to-Speech-Synthesis-for-Adversarial-Attacks
Cocii/hifi-gan
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
Language:Python0 0
Cocii/meldy
:notes: A mood-based melody generator
Language:Python0 0
Cocii/MIDI-Piano
Language:JavaScript1 0
Cocii/Project_Group7
The project of Group7(Jiayan and Axel)
Language:JavaScript1 0
Cocii/rawnet2
1 0
Cocii/so-vits-svc
SoftVC VITS Singing Voice Conversion
Language:Python0 0
Cocii/stable-diffusion-webui
Stable Diffusion web UI
Language:Python0 0
Cocii/TSSDNet
Time-domain synthetic speech detection net (TSSDNet), having the classic ResNet and Inception Net style structures (Res-TSSDNet and Inc-TSSDNet), for end-to-end synthetic speech detection. They achieve the state-of-the-art performance in terms of EER on ASVspoof 2019 challenge and promising generalization capability tested on ASVspoof 2015.