chenchengxin's Projects
Dilated Residual Networks
Source code for the paper "DSNet: Disentangled Siamese Network with Neutral Calibration for Speech Emotion Recognition".
This repository contains code to replicate results from the ICASSP 2020 paper "StarGAN for Emotional Speech Conversion: Validated by Data Augmentation of End-to-End Emotion Recognition".
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
Fully Convolutional Networks for Semantic Segmentation by Jonathan Long*, Evan Shelhamer*, and Trevor Darrell. CVPR 2015 and PAMI 2016.
Just another repository
Source code for the paper "Modality-collaborative Transformer with Hybrid Feature Reconstruction for Robust Emotion Recognition".
[ACL'19] [PyTorch] Multimodal Transformer
A No-Recurrence Sequence-to-Sequence Model for Speech Recognition
Python based importer of CSV files.
pytorch handbook是一本开源的书籍,目标是帮助那些希望和使用PyTorch进行深度学习开发和研究的朋友快速入门,其中包含的Pytorch教程全部通过测试保证可以成功运行
The lightweight PyTorch wrapper for high-performance AI research. Scale your models, not the boilerplate.
PyTorch Tutorial for Deep Learning Researchers
A library for soundscape synthesis and augmentation
SincNet is a neural architecture for efficiently processing raw audio samples.
Bidirectional LSTM network for speech emotion recognition.
An application that transforms the emotion component of speech into another specific target emotion.
A list of all named GANs!
Source code for the paper "TRNet: Two-level Refinement Network leveraging Speech Enhancement for Noise Robust Speech Emotion Recognition".