James Lin — accepted AI-conference papers

2020

FTL: A universal framework for training low-bit DNNs via Feature Transfer

Kunyuan Du, Ya Zhang, Haibing Guan, Qi Tian, Shenggan Cheng, James Lin

ECCV 2020poster

Low-bit Deep Neural Networks (low-bit DNNs) have recently received significant attention for their high efficiency. However, low-bit DNNs are often difficult to optimize due to the the saddle points in loss surfaces. Here we introduce a novel feature-based knowledge transfer framework, which utilize…

Cited by 1 Source ↗PDF ↗Scholar ↗

2020

Training Keyword Spotters with Limited and Synthesized Speech Data

James Lin, Kevin Kilgour, Dominik Roblek, Matthew Sharifi

ICASSP 2020accepted

With the rise of low power speech-enabled devices, there is a growing demand to quickly produce models for recognizing arbitrary sets of keywords. As with many machine learning tasks, one of the most challenging parts in the model creation process is obtaining a sufficient amount of training data. I…

Cited by 0 Source ↗Scholar ↗