Name: Grant Lee
Type: User
Company: Acoustics & Speech Group, AI Lab, Xiaomi Corporation
Bio: 2020 , AI Lab, Xiaomi Corporation, China
2015 - 2020, PhD Student, School of Computer Science, Wuhan University
Location: Wuhan, China
Grant Lee's Projects
A PyTorch implementation of Conv-TasNet described in "TasNet: Surpassing Ideal Time-Frequency Masking for Speech Separation" with Permutation Invariant Training (PIT).
The FADE simulation framework adapted to predict SRTs for the Hurricance 2.0 challenge
Fully-Convolutional Network for Pitch Estimation of Speech Signals
Implementation for paper "iMetricGAN: Intelligibility Enhancement for Speech-in-Noise using Generative Adversarial Network-based Metric Learning"
Basic Tools
Basic Tools
Neural Speech Codec
PyTorch implementations of Generative Adversarial Networks.
Fully reproduce the paper of StarGAN-VC. Stable training and Better audio quality .
PyTorch Tutorial for Deep Learning Researchers
WaveNet-Vocoder implementation with pytorch.
A PyTorch implementation of SEGAN based on INTERSPEECH 2017 paper "SEGAN: Speech Enhancement Generative Adversarial Network"
Contains code for our work on speech to singing conversion (ICASSP 2020)
Voice Converter Using CycleGAN and Non-Parallel Data