mlsanityData to 7 Oct 2026

TICL+: A Case Study On Speech In-Context Learning for Children's Speech Recognition

arXiv 2512.18263 ↗First posted 20 Dec 2025eess.AS cs.AI cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 17 of its 29 references that are in the map. First posted on arXiv 20 Dec 2025.

Builds on

17 of 29 references.

References · 17

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,371
  3. 2025Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAscited by 491
  4. 2024Many-Shot In-Context Learningcited by 203
  5. 2023Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong General Audio Event Taggerscited by 72
  6. 2023Can Whisper perform speech-based in-context learning?cited by 35
  7. 2023Kid-Whisper: Towards Bridging the Performance Gap in Automatic Speech Recognition for Children VS. Adultscited by 26
  8. 2023My Science Tutor (MyST) -- A Large Corpus of Children's Conversational Speechcited by 26
  9. 2023Adaptation of Whisper models to child speech recognitioncited by 25
  10. 2023Towards Better Domain Adaptation for Self-supervised Models: A Case Study of Child ASRcited by 23
  11. 2022DRAFT: A Novel Framework to Reduce Domain Shifting in Self-supervised Learning and Its Application to Children's ASRcited by 21
  12. 2022A Wav2vec2-Based Experimental Study on Self-Supervised Learning Methods to Improve Child Speech Recognitioncited by 15
5 more
  1. 2025In-Context Learning Boosts Speech Recognition via Human-like Adaptation to Speakers and Language Varietiescited by 7
  2. 2024M2R-Whisper: Multi-stage and Multi-scale Retrieval Augmentation for Enhancing Whispercited by 4
  3. 2024FASA: a Flexible and Automatic Speech Aligner for Extracting High-quality Aligned Children Speech Datacited by 3
  4. 2024Automatic Screening for Children with Speech Disorder using Automatic Speech Recognition: Opportunities and Challengescited by 3
  5. 2025TICL: Text-Embedding KNN For Speech In-Context Learning Unlocks Speech Recognition Abilities of Large Multimodal Modelscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026SALSA: Speech Aware LLM Adaptation via Learned Steering Activation Vectorscited by 2
  2. 2026MetaSICL: Globalizing Auditory LLMs for Underserved Speakers and Languages via Meta Speech In-Context Learningcited by 1
  3. 2026FSA-GRPO: Teaching Auditory LLMs to Use Few-Shot Demonstrationscited by 0
  4. 2026In-Context Adaptation of Encoder-Decoder Models in Speech Recognitioncited by 0