研究领域

Object Detection – Haar-Cascade, HOG-SVM, SSD, YOLO, YOLACT, Faster RCNN.

Automatic Speech Recognition – Wav2Letter, Deep Speech 1/2, LM, CTC Decoder

Beamforming – BeamformIt (Delay and Sum), Mask Estimation, NN-GEV, MVDR

Face Recognition – Spoof Detection, FaceNet, HOG+SVM, Cascading

Image Classification – ResNet, MobileNet V2

TTS, KWS, etc.

总结文章,核心概念,应用场景,优势劣势。