mlsanityData to 14 Oct 2026

Benchmarking Training Paradigms, Dataset Composition, and Model Scaling for Child ASR in ESPnet

arXiv 2508.16576 ↗First posted 22 Aug 2025cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Despite advancements in ASR, child speech recognition remains challenging due to acoustic variability and limited annotated data. While fine-tuning adult ASR models on child speech is common, comparisons with flat-start training remain underexplored. We compare flat-start training across multiple datasets, SSL representations (WavLM, XEUS), and decoder architectures. Our results show that SSL representations are biased toward adult speech, with flat-start training on child speech mitigating these biases. We also analyze model scaling, finding consistent improvements up to 1B parameters, beyond which performance plateaus. Additionally, age-related ASR and speaker verification analysis highlights the limitations of proprietary models like Whisper, emphasizing the need for open-data models for reliable child speech research. All investigations are conducted using ESPnet, and our publicly available benchmark provides insights into training strategies for robust child speech processing.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 28 of its 42 references that are in the map. First posted on arXiv 22 Aug 2025.

Builds on

28 of 42 references.

References · 28

  1. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  2. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  3. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  4. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,657
  5. 2021SUPERB: Speech processing Universal PERformance Benchmarkcited by 666
  6. 2018ESPnet: End-to-End Speech Processing Toolkitcited by 558
  7. 2019A Comparative Study on Transformer vs RNN in Speech Applicationscited by 211
  8. 2022E-Branchformer: Branchformer with Enhanced merging for speech recognitioncited by 92
  9. 2024OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformercited by 74
  10. 2022Pushing the limits of raw waveform speaker recognitioncited by 51
  11. 2024Towards Robust Speech Representation Learning for Thousands of Languagescited by 50
  12. 2023Reproducing Whisper-Style Training Using an Open-Source Toolkit and Publicly Available Datacited by 42
16 more
  1. 2024OWSM-CTC: An Open Encoder-Only Speech Foundation Model for Speech Recognition, Translation, and Language Identificationcited by 37
  2. 2024Benchmarking Children's ASR with Supervised and Self-supervised Speech Foundation Modelscited by 29
  3. 2023Exploration of Efficient End-to-End ASR using Discretized Input from Self-Supervised Learningcited by 28
  4. 2023My Science Tutor (MyST) -- A Large Corpus of Children's Conversational Speechcited by 28
  5. 2023Kid-Whisper: Towards Bridging the Performance Gap in Automatic Speech Recognition for Children VS. Adultscited by 27
  6. 2024ML-SUPERB 2.0: Benchmarking Multilingual Speech Models Across Modeling Constraints, Languages, and Datasetscited by 27
  7. 2023Towards Universal Speech Discrete Tokens: A Case Study for ASR and TTScited by 24
  8. 2023Towards Better Domain Adaptation for Self-supervised Models: A Case Study of Child ASRcited by 23
  9. 2018Transfer Learning from Adult to Children for Speech Recognition: Evaluation, Analysis and Recommendationscited by 22
  10. 2024ESPnet-SPK: full pipeline speaker embedding toolkit with reproducible recipes, self-supervised front-ends, and off-the-shelf modelscited by 22
  11. 2023Speech Self-Supervised Representations Benchmarking: a Case for Larger Probing Headscited by 17
  12. 2025OWLS: Scaling Laws for Multilingual Speech Recognition and Translation Modelscited by 17
  13. 2022A Wav2vec2-Based Experimental Study on Self-Supervised Learning Methods to Improve Child Speech Recognitioncited by 15
  14. 2024On the Evaluation of Speech Foundation Models for Spoken Language Understandingcited by 9
  15. 2024Analysis of Self-Supervised Speech Models on Children's Speech and Infant Vocalizationscited by 7
  16. 2024ChildAugment: Data Augmentation Methods for Zero-Resource Children's Speaker Verificationcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026Mind the Shift: Using Delta SSL Embeddings to Enhance Child ASRcited by 3
  2. 2026SSVD-O: Parameter-Efficient Fine-Tuning with Structured SVD for Speech Recognitioncited by 1
  3. 2026Entropy-Aware Domain-Routed Mixture-of-Experts Speech-LLM Framework: A Case Study of Multi-Domain Child-Adult ASRcited by 1
  4. 2026Gumbel-BEARD: Automatic Layer Selection for Self-Supervised Adaptation of Whisper in Low-Resource Domainscited by 1
  5. 2026Encoder Awakening via Adapters: Effective Domain-Adaptive Fine-tuning of Speech-LLMscited by 0
  6. 2026AURA: Uncertainty-Routed Activation Editing for Acoustic Grounding in Speech Foundation Modelscited by 0