Xinsheng Wang

Pytorch Code for S2IGAN

A pitch detection model trained to be robust against noise and reverberation environments.

ICASSP 2021 accepted papers in term of voice conversion (VC)

No description.

Tacotron series TTS model implemented with Pytorch

No description.

Pytorch tacotron2 that can be used to perform batch inference

No description.

pytorch implementation of ObamaNet

Rotate 3D face landmarks to front

No description.

word boundary discovery in continuous speech signal

No description.

The code is for the No-audio Speech Detection task in MediaEval 2020

Progressively Growing GAN in PyTorch for Image and Sound generation

No description.

Data augmentation tool for images

Generative Dual Adversarial Network for Generalized Zero-shot Learning

This is an implementation of the Extreme Value Machine by Rudd et al., with minor changes from the original work.

Pytorch implementation of deep person re-identification models.

Personal webpage

:orange_book: 中华新华字典数据库。包括歇后语，成语，词语，汉字。

📝 Easily create a beautiful website using Academic, Hugo, and Netlify

No description.

An open-source high-quality Mandarin singing voice synthesis corpus

DDSP: Differentiable Digital Signal Processing

No description.

Jamstack site created with Stackbit

VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

A Generative Flow for Text-to-Speech via Monotonic Alignment Search

PyTorch Implementation of PortaSpeech: Portable and High-Quality Generative Text-to-Speech

FECNet to extract facial expression features

Real Time Speech Enhancement in the Waveform Domain (Interspeech 2020)We provide a PyTorch implementation of the paper Real Time Speech Enhancement in the Waveform Domain. In which, we present a causal speech enhancement model working on the raw waveform that runs in real-time on a laptop CPU. The proposed model is based on an encoder-decoder architecture with skip-connections. It is optimized on both time and frequency domains, using multiple loss functions. Empirical evidence shows that it is capable of removing various kinds of background noise including stationary and non-stationary noises, as well as room reverb. Additionally, we suggest a set of data augmentation techniques applied directly on the raw waveform which further improve model performance and its generalization abilities.

Papers submitted to Interspeech 2021 in terms of text-to-speech (TTS) and voice conversion (VC)

TTS papers accepted to ICASSP 2021

CN-Celeb, a large-scale Chinese celebrities dataset published by Center for Speech and Language Technology (CSLT) at Tsinghua University.

This repository contains the source code for the paper First Order Motion Model for Image Animation

微软edx语音识别课程

Kaldi 入门教程

A PyTorch implementation of Listen, Attend and Spell (LAS), an End-to-End ASR framework.

No description.

A curated list of papers & ressources linked to open set recognition and open world recognition

No description.

The implementation of "End-to-End Multi-Task Learning with Attention" [CVPR'19].

A curated list of papers, code and resources pertaining to zero shot learning

Pytorch code for CVPR 2017 paper: Learning a Deep Embedding Model for Zero-Shot Learning

Siamese and triplet networks with online pair/triplet mining in PyTorch

The most cited deep learning papers

Repository for deep zero-shot learning via cross-modality transfer

Semantic Autoencoder for Zero-shot Learning (Spotlight), CVPR 2017

No description.

Code for the paper: Audio-Visual Scene Analysis with Self-Supervised Multisensory Features

记录每天整理的计算机视觉/深度学习/机器学习相关方向的论文

image retrieval

Using siamese network to do dimensionality reduction and similar image retrieval

Models and examples built with TensorFlow

整理和注释了facenet的代码，以便更好地理解facenet的代码。源代码地址：https://github.com/davidsandberg/facenet

A simplified implemention of Faster R-CNN that replicate performance from origin paper

Tensorflow Implementation of the Semantic Segmentation DeepLab_V3 CNN

No description.

No description.

No description.

No description.