Deep Learning for Assessment of Oral Reading Fluency

TL;DR

This paper explores automatic assessment of children's oral reading fluency using deep learning, leveraging pre-trained models and analyzing acoustic features to improve scalability and objectivity in literacy evaluation.

Contribution

It introduces an end-to-end deep learning approach with wav2vec2.0 for reading fluency assessment, addressing data limitations and analyzing relevant acoustic and lexical features.

Findings

Pre-trained wav2vec2.0 improves fluency assessment accuracy.

Acoustic-prosodic features are significant for fluency perception.

System variations show promising performance on fluency measures.

Abstract

Reading fluency assessment is a critical component of literacy programmes, serving to guide and monitor early education interventions. Given the resource intensive nature of the exercise when conducted by teachers, the development of automatic tools that can operate on audio recordings of oral reading is attractive as an objective and highly scalable solution. Multiple complex aspects such as accuracy, rate and expressiveness underlie human judgements of reading fluency. In this work, we investigate end-to-end modeling on a training dataset of children's audio recordings of story texts labeled by human experts. The pre-trained wav2vec2.0 model is adopted due its potential to alleviate the challenges from the limited amount of labeled data. We report the performance of a number of system variations on the relevant measures, and also probe the learned embeddings for lexical and acoustic-prosodic features known to be important to the perception of reading fluency.