Leveraging End-to-End Speech Recognition with Neural Architecture Search

12/11/2019

∙

by   Ahmed Baruwa, et al.

∙

0

∙

share

Deep neural networks (DNNs) have been demonstrated to outperform many traditional machine learning algorithms in Automatic Speech Recognition (ASR). In this paper, we show that a large improvement in the accuracy of deep speech models can be achieved with effective Neural Architecture Optimization at a very low computational cost. Phone recognition tests with the popular LibriSpeech and TIMIT benchmarks proved this fact by displaying the ability to discover and train novel candidate models within a few hours (less than a day) many times faster than the attention-based seq2seq models. Our method achieves test error of 7 Error Rate (PER) on the TIMIT corpus, on par with state-of-the-art results.