# Towards Real-time Mispronunciation Detection in Kids' Speech

arXiv: https://arxiv.org/abs/2003.01765 · HTML: https://mlsanity.com/paper/2003.01765/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Mar 2020.

## Built on by (most cited first, 8 of 8)

- [Bayes risk CTC: Controllable CTC alignment in Sequence-to-Sequence tasks](https://mlsanity.com/paper/2210.07499/) (2022)
- [Weakly-supervised word-level pronunciation error detection in non-native English speech](https://mlsanity.com/paper/2106.03494/) (2021)
- [Computer-assisted Pronunciation Training -- Speech synthesis is almost all you need](https://mlsanity.com/paper/2207.00774/) (2022)
- ['Beach' to 'Bitch': Inadvertent Unsafe Transcription of Kids' Content on YouTube](https://mlsanity.com/paper/2203.04837/) (2022)
- [End-to-End real time tracking of children's reading with pointer network](https://mlsanity.com/paper/2310.11486/) (2023)
- [A Differentiable Alignment Framework for Sequence-to-Sequence Modeling via Optimal Transport](https://mlsanity.com/paper/2502.01588/) (2025)
- [KidSpeak: A General Multi-purpose LLM for Kids' Speech Recognition and Screening](https://mlsanity.com/paper/2512.05994/) (2025)
- [Light-weight Pronunciation Assessment via Discrete Speech Token Surprisal](https://mlsanity.com/paper/2606.19910/) (2026)

## Abstract (arXiv)

Modern mispronunciation detection and diagnosis systems have seen significant gains in accuracy due to the introduction of deep learning. However, these systems have not been evaluated for the ability to be run in real-time, an important factor in applications that provide rapid feedback. In particular, the state-of-the-art uses bi-directional recurrent networks, where a uni-directional network may be more appropriate. Teacher-student learning is a natural approach to use to improve a uni-directional model, but when using a CTC objective, this is limited by poor alignment of outputs to evidence. We address this limitation by trying two loss terms for improving the alignments of our models. One loss is an "alignment loss" term that encourages outputs only when features do not resemble silence. The other loss term uses a uni-directional model as teacher model to align the bi-directional model. Our proposed model uses these aligned bi-directional models as teacher models. Experiments on the CSLU kids' corpus show that these changes decrease the latency of the outputs, and improve the detection rates, with a trade-off between these goals.