# Child ASR Adaptation with Adult Retention: An Empirical Study

arXiv: https://arxiv.org/abs/2610.08827 · HTML: https://mlsanity.com/paper/2610.08827/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 41 references that are in the map.
- First posted on arXiv 25 Sep 2026.

## Builds on (most cited first, 26 of 26)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time](https://mlsanity.com/paper/2203.05482/) (2022)
- [TIES-Merging: Resolving Interference When Merging Models](https://mlsanity.com/paper/2306.01708/) (2023)
- [Towards One Model to Rule All: Multilingual Strategy for Dialectal Code-Switching Arabic ASR](https://mlsanity.com/paper/2105.14779/) (2021)
- [OWSM-CTC: An Open Encoder-Only Speech Foundation Model for Speech Recognition, Translation, and Language Identification](https://mlsanity.com/paper/2402.12654/) (2024)
- [My Science Tutor (MyST) -- A Large Corpus of Children's Conversational Speech](https://mlsanity.com/paper/2309.13347/) (2023)
- [Kid-Whisper: Towards Bridging the Performance Gap in Automatic Speech Recognition for Children VS. Adults](https://mlsanity.com/paper/2309.07927/) (2023)
- [Adaptation of Whisper models to child speech recognition](https://mlsanity.com/paper/2307.13008/) (2023)
- [The MGB-2 Challenge: Arabic Multi-Dialect Broadcast Media Recognition](https://mlsanity.com/paper/1609.05625/) (2016)
- [Transfer Learning from Adult to Children for Speech Recognition: Evaluation, Analysis and Recommendations](https://mlsanity.com/paper/1805.03322/) (2018)
- [End-to-End Neural Systems for Automatic Children Speech Recognition: An Empirical Study](https://mlsanity.com/paper/2102.09918/) (2021)
- [TLT-school: a Corpus of Non Native Children Speech](https://mlsanity.com/paper/2001.08051/) (2020)
- [Selective Attention Merging for low resource tasks: A case study of Child ASR](https://mlsanity.com/paper/2501.08468/) (2025)
- [Children's Speech Recognition through Discrete Token Enhancement](https://mlsanity.com/paper/2406.13431/) (2024)
- [Improving Children's Speech Recognition by Fine-tuning Self-supervised Adult Speech Representations](https://mlsanity.com/paper/2211.07769/) (2022)
- [Arabic Little STT: Arabic Children Speech Recognition Dataset](https://mlsanity.com/paper/2510.23319/) (2025)
- [Multi-Task Instruction Tuning via Data Scheduling for Low-Resource Arabic SpeechLLMs](https://mlsanity.com/paper/2601.12494/) (2026)
- [Continual learning using lattice-free MMI for speech recognition](https://mlsanity.com/paper/2110.07055/) (2021)
- [HARNESS: Lightweight Distilled Arabic Speech Foundation Models](https://mlsanity.com/paper/2509.14689/) (2025)

## Abstract (arXiv)

Automatic Speech Recognition (ASR) systems often underperform for children and non-native speakers, while adapting adult ASR models to child speech can cause adult-speech forgetting. We study child ASR adaptation with adult retention across Arabic and English. We compare full fine-tuning, LoRA, and post-hoc weight-space merging across encoder--decoder, encoder--CTC, and AudioLLM-based ASR systems. Experiments use Arabic native and non-native child speech, English MyST child speech, and adult benchmarks from MGB-2 and LibriSpeech test-clean. We evaluate recognition quality with WER and quantify the adaptation--retention trade-off using Retention Index, Child Adaptation Gain, and Adaptation Recovery. Results show that child adaptation is necessary, especially for non-native Arabic and English child speech, but direct adaptation often reduces adult ASR performance. Bilingual adaptation is more stable than language-specific adaptation. Weight-space merging often improves the trade-off, especially for encoder--CTC, Whisper, and AudioLLM-based ASR, with LERP favoring adult retention and TIES recovering stronger child gains. For the encoder--decoder model, direct bilingual fine-tuning remains strongest in raw WER.footnoteCode, and models are available at https://github.com/qcri/Child-ASR-Adaptation.