# Building an ASR Solution for Training and Assessing Children's Reading

arXiv: https://arxiv.org/abs/2606.31508 · HTML: https://mlsanity.com/paper/2606.31508/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 26 references that are in the map.
- First posted on arXiv 30 Jun 2026.

## Builds on (most cited first, 11 of 11)

- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition](https://mlsanity.com/paper/2305.05084/) (2023)
- [QuartzNet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions](https://mlsanity.com/paper/1910.10261/) (2019)
- [Efficient Sequence Transduction by Jointly Predicting Tokens and Durations](https://mlsanity.com/paper/2304.06795/) (2023)
- [Dissecting User-Perceived Latency of On-Device E2E Speech Recognition](https://mlsanity.com/paper/2104.02207/) (2021)
- [Automatic Assessment of Oral Reading Accuracy for Reading Diagnostics](https://mlsanity.com/paper/2306.03444/) (2023)
- [Automatic Speech Recognition (ASR) for African Low-Resource Languages: A Systematic Literature Review](https://mlsanity.com/paper/2510.01145/) (2025)
- [Dealing with the Hard Facts of Low-Resource African NLP](https://mlsanity.com/paper/2511.18557/) (2025)
- [Kunnafonidilaw ka Cadeau: an ASR dataset of present-day Bambara](https://mlsanity.com/paper/2512.19400/) (2025)
- [Deep Learning for Assessment of Oral Reading Fluency](https://mlsanity.com/paper/2405.19426/) (2024)
- [Where Are We At with Automatic Speech Recognition for the Bambara Language?](https://mlsanity.com/paper/2602.09785/) (2026)

## Abstract (arXiv)

Automatic speech recognition for children's reading remains underdeveloped for most African languages, including Bambara, despite its potential value for reproducible literacy assessment. We present an open-source system for assessing children's reading in Bambara, developed through an end-to-end process linking field data collection, benchmark construction, model adaptation, a reading application, and classroom validation. A mobile collection and assessment app was used to collect 55 hours of raw reading speech from 60 children, from which we construct a public benchmark for Bambara child-reading assessment. Fine-tuning experiments compare Soloni, a Bambara-adapted Fast-Conformer ASR framework with TDT and CTC decoders, with QuartzNet, a compact convolutional ASR architecture. The best Soloni model reduces WER from 0.42 to 0.22 and CER from 0.15 to 0.08, substantially outperforming QuartzNet on the isolated benchmark. The experiments further show that repeated readings of the same texts provide architecture-dependent benefits: they substantially improve QuartzNet but add only marginal gains for Soloni, while SpecAugment regulates training without exceeding the best unaugmented configuration. Disaggregated analysis identifies children under 10 as the main source of residual errors, motivating targeted collection from younger readers. Ten classroom trials supported continued use of the application.