I am an experienced Data Scientist in data prediction, computer vision and speech processing with deep learning.
I have been studying Deep Learning for several years and use TensorFlow and PyTorch.
Typical repositories I researched are as follows.
-Image classification DNNs Submitted at ILSVRC: VGG, Inception, Resnet, Mobilenet, Densenet, Alexnet, Cifarnet
-object detection DNNs: Mask_RCNN, SSD-Tensorflow, Yolo
-image segmentation DNNs: Mask_RCNN
-OCR: tesseract, East, R2CNN
-Speech Recognition: Deepspeech, Deepspeech2, End-to-end-ASR-Pytorch, Returnn, espnet
-Speech synthesis: Tacotron-2, Fastspeech2
-Speech denoising: DNSChallenge, segan, sednn
-Acoustic echo canceller: AECChallenge
-Voice Conversion: CVC, CycleGAN-VC2
-Vocoder: Parallel WaveGAN, MelGAN
-Scene Text Understanding: EAST
I can work with teammates through Github and Google Colab.
Thanks for your regards.