Semi-supervised and Population Based Training for Voice Commands Recognition
This incremental work addresses efficient and accurate voice command recognition for hardware-constrained applications.
The paper tackled voice command classification by combining semi-supervised training with automated hyper-parameter tuning, improving accuracy from 84% to 94% on a validation set and enabling optimized model training in the time of a single model.
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.