# Semi-supervised and Population Based Training for Voice Commands Recognition

## TL;DR

This paper introduces a rapid, semi-supervised, and population-based training approach for voice command recognition that enhances accuracy and optimizes models efficiently for real-world hardware constraints.

## Contribution

It combines automated hyper-parameter tuning with semi-supervised learning to quickly evaluate and optimize voice recognition models for specific performance and power needs.

## Key findings

- Classification accuracy improved from 84% to 94%.
- Semi-supervised training effectively leverages unlabeled data.
- Population based training finds optimized models efficiently.

## 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.