papers AI Learner
The Github is limit! Click to go to the new site.

Semi-supervised and Population Based Training for Voice Commands Recognition

2019-05-10
Oguz H. Elibol, Gokce Keskin, Anil Thomas

Abstract

We present a rapid design methodology that combines automated hyper-parameter tuning with semi-supervised training to build highly accurate and robust models for voice commands classification. Proposed approach allows quick evaluation of network architectures to fit performance and power constraints of available hardware, while ensuring good hyper-parameter choices for each network in real-world scenarios. Leveraging the vast amount of unlabeled data with a student/teacher based semi-supervised method, classification accuracy is improved from 84% to 94% in the validation set. For model optimization, we explore the hyper-parameter space through population based training and obtain an optimized model in the same time frame as it takes to train a single model.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1905.04230

PDF

http://arxiv.org/pdf/1905.04230


Similar Posts

Comments