TICL+: A Case Study On Speech In-Context Learning for Children's Speech Recognition
Abstract
Children's speech recognition remains challenging due to substantial acoustic and linguistic variability, limited labeled data, and significant differences from adult speech. Speech foundation models can address these challenges through Speech In-Context Learning (SICL), allowing adaptation to new domains without fine-tuning. However, the effectiveness of SICL depends on how in-context examples are selected. We extend an existing retrieval-based method, Text-Embedding KNN for SICL (TICL), introducing an acoustic reranking step to create TICL+. This extension prioritizes examples that are both semantically and acoustically aligned with the test input. Experiments on four children's speech corpora show that TICL+ achieves up to a 53.3% relative word error rate reduction over zero-shot performance and 37.6% over baseline TICL, highlighting the value of combining semantic and acoustic information for robust, scalable ASR in children's speech.
Keywords
Cite
@article{arxiv.2512.18263,
title = {TICL+: A Case Study On Speech In-Context Learning for Children's Speech Recognition},
author = {Haolong Zheng and Yekaterina Yegorova and Mark Hasegawa-Johnson},
journal= {arXiv preprint arXiv:2512.18263},
year = {2025}
}
Comments
Published at IEEE ASRU 2025 Satellite Workshop-AI for Children's Speech and Language