A Survey of Recent DNN Architectures on the TIMIT Phone Recognition Task

TL;DR

This survey evaluates recent deep neural network architectures on the TIMIT phone recognition task, providing a baseline with open-source scripts and achieving lower error rates than previous reports.

Contribution

It offers a comprehensive comparison of recent DNN architectures on TIMIT, establishing a new baseline with open-source code and improved performance.

Findings

Achieved the lowest phone error rate (PER) to date on TIMIT.

Provided open-source scripts for replicating baseline results.

Compared various DNN architectures and identified top performers.

Abstract

In this survey paper, we have evaluated several recent deep neural network (DNN) architectures on a TIMIT phone recognition task. We chose the TIMIT corpus due to its popularity and broad availability in the community. It also simulates a low-resource scenario that is helpful in minor languages. Also, we prefer the phone recognition task because it is much more sensitive to an acoustic model quality than a large vocabulary continuous speech recognition (LVCSR) task. In recent years, many DNN published papers reported results on TIMIT. However, the reported phone error rates (PERs) were often much higher than a PER of a simple feed-forward (FF) DNN. That was the main motivation of this paper: To provide a baseline DNNs with open-source scripts to easily replicate the baseline results for future papers with lowest possible PERs. According to our knowledge, the best-achieved PER of this survey is better than the best-published PER to date.