You Zhang's repositories
AIR-ASVspoof
Official implementation of the SPL paper "One-class Learning Towards Synthetic Voice Spoofing Detection"
ASVspoof2021_AIR
Official implementation of our ASVspoof 2021 paper, "UR Channel-Robust Synthetic Speech Detection System for ASVspoof 2021"
Audio_Research_in_US
For students who would like to apply for RA, PhD, postdoc in audio research.
hrtf_field
Official implementation of the ICASSP 2023 paper "HRTF Field: Unifying Measured HRTF Magnitude Representation with Neural Fields"
Empirical-Channel-CM
Official Implementation of our Interspeech 2021 paper "An Empirical Study on Channel Effects for Synthetic Voice Spoofing Countermeasure Systems"
CS61Bsp18-proj2-byog
Project BYoG for UCB course CS61B Data Structures Spring 2018
HBAS_chapter_voice3
Official implementation of the handbook chapter "Generalizing Voice Presentation Attack Detection to Unseen Synthetic Attacks and Channel Variation"
HRTF_field_norm
Official Implementation of our WASPAA 2023 paper "Mitigating Cross-Database Differences for Learning Unified HRTF Representation"
awesome-audio-visual
A curated list of different papers and datasets in various areas of audio-visual processing
awesome-diarization
A curated list of awesome Speaker Diarization papers, libraries, datasets, and other resources.
INFO159-LHW4-Chatbot
A pytorch Chatbot for INFO159 Natural Language Processing
PhaseAntispoofing_INTERSPEECH
Official repository of the Interspeech 2023 paper "Phase perturbation improves channel robustness for speech spoofing countermeasures"
DiffGAN-TTS
PyTorch Implementation of DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANs
espnet
End-to-End Speech Processing Toolkit
FastDiff
PyTorch Implementation of FastDiff (IJCAI'22)
flowtron
Flowtron is an auto-regressive flow-based generative network for text to speech synthesis with control over speech variation and style transfer
mellotron
Mellotron: a multispeaker voice synthesis model based on Tacotron 2 GST that can make a voice emote and sing without emotive or singing training data
Online-Recurrent-Extreme-Learning-Machine
Online-Recurrent-Extreme-Learning-Machine (OR-ELM) for time-series prediction, implemented in python
samo
SAMO: SPEAKER ATTRACTOR MULTI-CENTER ONE-CLASS LEARNING FOR VOICE ANTI-SPOOFING
serve
Serve, optimize and scale PyTorch models in production
SingFake
Official Repository for "SingFake: Singing Voice Deepfake Detection"
SpeechTasks
This is a list of speech tasks and datasets, which can provide training data for Generative AI, AIGC, AI model training, intelligent speech tool development, and speech applications.