How does the teacher rate? Observations from the NeuroPiano dataset

TL;DR

This paper analyzes the NeuroPiano dataset of student piano performances, examining annotations, inter-annotator agreement, and predicting teacher ratings from audio features using machine learning.

Contribution

It provides a comprehensive statistical overview of the dataset and explores the predictive relationship between audio features and teacher ratings.

Findings

High inter-annotator agreement on performance quality

Successful prediction of ratings from audio features

Insights into textual feedback patterns

Abstract

This paper provides a detailed analysis of the NeuroPiano dataset, which comprise 104 audio recordings of student piano performances accompanied with 2255 textual feedback and ratings given by professional pianists. We offer a statistical overview of the dataset, focusing on the standardization of annotations and inter-annotator agreement across 12 evaluative questions concerning performance quality. We also explore the predictive relationship between audio features and teacher ratings via machine learning, as well as annotations provided for text analysis of the responses.