# Mind the Shift: Using Delta SSL Embeddings to Enhance Child ASR

arXiv: https://arxiv.org/abs/2601.20142 · HTML: https://mlsanity.com/paper/2601.20142/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 40 references that are in the map.
- First posted on arXiv 28 Jan 2026.

## Builds on (most cited first, 27 of 27)

- [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)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language](https://mlsanity.com/paper/2202.03555/) (2022)
- [Insights on representational similarity in neural networks with canonical correlation](https://mlsanity.com/paper/1806.05759/) (2018)
- [Layer-wise Analysis of a Self-supervised Speech Representation Model](https://mlsanity.com/paper/2107.04734/) (2021)
- [Self-Supervised Speech Representation Learning: A Review](https://mlsanity.com/paper/2205.10643/) (2022)
- [Comparative layer-wise analysis of self-supervised speech models](https://mlsanity.com/paper/2211.03929/) (2022)
- [What Do Self-Supervised Speech Models Know About Words?](https://mlsanity.com/paper/2307.00162/) (2023)
- [Benchmarking Children's ASR with Supervised and Self-supervised Speech Foundation Models](https://mlsanity.com/paper/2406.10507/) (2024)
- [Kid-Whisper: Towards Bridging the Performance Gap in Automatic Speech Recognition for Children VS. Adults](https://mlsanity.com/paper/2309.07927/) (2023)
- [Combining Spectral and Self-Supervised Features for Low Resource Speech Recognition and Translation](https://mlsanity.com/paper/2204.02470/) (2022)
- [CPT-Boosted Wav2vec2.0: Towards Noise Robust Speech Recognition for Classroom Environments](https://mlsanity.com/paper/2409.14494/) (2024)
- [Investigation of Ensemble features of Self-Supervised Pretrained Models for Automatic Speech Recognition](https://mlsanity.com/paper/2206.05518/) (2022)
- [Towards Robust Family-Infant Audio Analysis Based on Unsupervised Pretraining of Wav2vec 2.0 on Large-Scale Unlabeled Family Audio](https://mlsanity.com/paper/2305.12530/) (2023)
- [Selective Attention Merging for low resource tasks: A case study of Child ASR](https://mlsanity.com/paper/2501.08468/) (2025)
- [Self-Supervised Models for Phoneme Recognition: Applications in Children's Speech for Reading Learning](https://mlsanity.com/paper/2503.04710/) (2025)
- [Benchmarking Training Paradigms, Dataset Composition, and Model Scaling for Child ASR in ESPnet](https://mlsanity.com/paper/2508.16576/) (2025)
- [FeaRLESS: Feature Refinement Loss for Ensembling Self-Supervised Learning Features in Robust End-to-end Speech Recognition](https://mlsanity.com/paper/2206.15056/) (2022)
- [Iterative refinement, not training objective, makes HuBERT behave differently from wav2vec 2.0](https://mlsanity.com/paper/2508.08110/) (2025)
- [EFFUSE: Efficient Self-Supervised Feature Fusion for E2E ASR in Low Resource and Multilingual Scenarios](https://mlsanity.com/paper/2310.03938/) (2023)
- [Robust fine-tuning of speech recognition models via model merging: application to disordered speech](https://mlsanity.com/paper/2505.20477/) (2025)
- [Exploring Effective Fusion Algorithms for Speech Based Self-Supervised Learning Models](https://mlsanity.com/paper/2212.10092/) (2022)
- [Delta Embedding Learning](https://mlsanity.com/paper/1812.04160/) (2018)
- [AC-Mix: Self-Supervised Adaptation for Low-Resource Automatic Speech Recognition using Agnostic Contrastive Mixup](https://mlsanity.com/paper/2410.14910/) (2024)
- [Can Layer-wise SSL Features Improve Zero-Shot ASR Performance for Children's Speech?](https://mlsanity.com/paper/2508.21225/) (2025)

## Built on by (most cited first, 3 of 3)

- [Entropy-Aware Domain-Routed Mixture-of-Experts Speech-LLM Framework: A Case Study of Multi-Domain Child-Adult ASR](https://mlsanity.com/paper/2606.10454/) (2026)
- [Gumbel-BEARD: Automatic Layer Selection for Self-Supervised Adaptation of Whisper in Low-Resource Domains](https://mlsanity.com/paper/2606.11429/) (2026)
- [Edge Phoneme Recognition for Children's Speech through Age-Aware Training](https://mlsanity.com/paper/2608.10206/) (2026)

## Abstract (arXiv)

Self-supervised learning (SSL) models have achieved impressive results across many speech tasks, yet child automatic speech recognition (ASR) remains challenging due to limited data and pretraining domain mismatch. Fine-tuning SSL models on child speech induces shifts in the representation space. We hypothesize that delta SSL embeddings, defined as the differences between embeddings from a finetuned model and those from its pretrained counterpart, encode task-specific information that complements finetuned features from another SSL model. We evaluate multiple fusion strategies on the MyST childrens corpus using different models. Results show that delta embedding fusion with WavLM yields up to a 10 percent relative WER reduction for HuBERT and a 4.4 percent reduction for W2V2, compared to finetuned embedding fusion. Notably, fusing WavLM with delta W2V2 embeddings achieves a WER of 9.64, setting a new state of the art among SSL models on the MyST corpus. These findings demonstrate the effectiveness of delta embeddings and highlight feature fusion as a promising direction for advancing child ASR.