Matthew Mulholland

A comparison of ASR and human errors for transcription of non-native spontaneous speech

2016

In this paper, we compare ASR and human transcriptions of non-native speech to investigate to what extent the accuracy and the patterns of errors of a modern ASR system match those of human listeners in …

A Robust Microservice Architecture for Scaling Automated Scoring Applications

2018 · ETS Research Report Series

Abstract We present a microservice architecture for large‐scale automated scoring applications. Our architecture builds on the open‐source Apache Storm framework and facilitates the development of robust, scalable automated scoring applications that can easily be extended …