# Automatic Detection and Analysis of Singing Mistakes for Music Pedagogy

arXiv: https://arxiv.org/abs/2602.06917 · HTML: https://mlsanity.com/paper/2602.06917/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 55 references that are in the map.
- First posted on arXiv 6 Feb 2026.

## Builds on (most cited first, 12 of 12)

- [Temporal Convolutional Networks for Action Segmentation and Detection](https://mlsanity.com/paper/1611.05267/) (2016)
- [Sound Event Detection: A Tutorial](https://mlsanity.com/paper/2107.05463/) (2021)
- [SyncNet: correlating objective for time delay estimation in audio signals](https://mlsanity.com/paper/2203.14639/) (2022)
- [An Interdisciplinary Review of Music Performance Analysis](https://mlsanity.com/paper/2104.09018/) (2021)
- [Automatic Pronunciation Assessment -- A Review](https://mlsanity.com/paper/2310.13974/) (2023)
- [Explainable Deep Learning Analysis for Raga Identification in Indian Art Music](https://mlsanity.com/paper/2406.02443/) (2024)
- [Analysis and Detection of Singing Techniques in Repertoires of J-POP Solo Singers](https://mlsanity.com/paper/2210.17367/) (2022)
- [Recognizing Ornaments in Vocal Indian Art Music with Active Annotation](https://mlsanity.com/paper/2505.04419/) (2025)
- [Score-informed Networks for Music Performance Assessment](https://mlsanity.com/paper/2008.00203/) (2020)
- [Score difficulty analysis for piano performance education based on fingering](https://mlsanity.com/paper/2203.13010/) (2022)
- [Balanced Deep CCA for Bird Vocalization Detection](https://mlsanity.com/paper/2211.09376/) (2022)
- [Decoupling and Interacting Multi-Task Learning Network for Joint Speech and Accent Recognition](https://mlsanity.com/paper/2311.07062/) (2023)

## Abstract (arXiv)

The advancement of machine learning in audio analysis has opened new possibilities for technology-enhanced music education. This paper introduces a framework for automatic singing mistake detection in the context of music pedagogy, supported by a newly curated dataset. The dataset comprises synchronized teacher learner vocal recordings, with annotations marking different types of mistakes made by learners. Using this dataset, we develop different deep learning models for mistake detection and benchmark them. To compare the efficacy of mistake detection systems, a new evaluation methodology is proposed. Experiments indicate that the proposed learning-based methods are superior to rule-based methods. A systematic study of errors and a cross-teacher study reveal insights into music pedagogy that can be utilised for various music applications. This work sets out new directions of research in music pedagogy. The codes and dataset are publicly available.