# Transfer Learning from Adult to Children for Speech Recognition: Evaluation, Analysis and Recommendations

arXiv: https://arxiv.org/abs/1805.03322 · HTML: https://mlsanity.com/paper/1805.03322/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 May 2018.

## Built on by (most cited first, 22 of 22)

- [Benchmarking Children's ASR with Supervised and Self-supervised Speech Foundation Models](https://mlsanity.com/paper/2406.10507/) (2024)
- [Deep Transfer Learning for Automatic Speech Recognition: Towards Better Generalization](https://mlsanity.com/paper/2304.14535/) (2023)
- [Adaptation of Whisper models to child speech recognition](https://mlsanity.com/paper/2307.13008/) (2023)
- [Cross-domain Speech Recognition with Unsupervised Character-level Distribution Matching](https://mlsanity.com/paper/2104.07491/) (2021)
- [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)
- [Bi-APC: Bidirectional Autoregressive Predictive Coding for Unsupervised Pre-training and Its Application to Children's ASR](https://mlsanity.com/paper/2102.06816/) (2021)
- [Speech Recognition for Automatically Assessing Afrikaans and isiXhosa Preschool Oral Narratives](https://mlsanity.com/paper/2501.06478/) (2025)
- [A comparative analysis between Conformer-Transducer, Whisper, and wav2vec2 for improving the child speech recognition](https://mlsanity.com/paper/2311.04936/) (2023)
- [Automatic Speech Recognition of African American English: Lexical and Contextual Effects](https://mlsanity.com/paper/2506.06888/) (2025)
- [Evaluation of Speech Foundation Models for ASR on Child-Adult Conversations in Autism Diagnostic Sessions](https://mlsanity.com/paper/2409.16135/) (2024)
- [Gumbel-BEARD: Automatic Layer Selection for Self-Supervised Adaptation of Whisper in Low-Resource Domains](https://mlsanity.com/paper/2606.11429/) (2026)
- [Social Fraud Detection Review: Methods, Challenges and Analysis](https://mlsanity.com/paper/2111.05645/) (2021)
- [Filter-based Discriminative Autoencoders for Children Speech Recognition](https://mlsanity.com/paper/2204.00164/) (2022)
- [Speaker- and Age-Invariant Training for Child Acoustic Modeling Using Adversarial Multi-Task Learning](https://mlsanity.com/paper/2210.10231/) (2022)
- [Inspecting Spoken Language Understanding from Kids for Basic Math Learning at Home](https://mlsanity.com/paper/2306.00482/) (2023)
- [Error-preserving Automatic Speech Recognition of Young English Learners' Language](https://mlsanity.com/paper/2406.03235/) (2024)
- [Designing the virtual CAT: A digital tool for algorithmic thinking assessment in compulsory education](https://mlsanity.com/paper/2408.01263/) (2024)
- [An End-to-End Approach for Child Reading Assessment in the Xhosa Language](https://mlsanity.com/paper/2505.17371/) (2025)
- [Speech Separation for Hearing-Impaired Children in the Classroom](https://mlsanity.com/paper/2511.07677/) (2025)
- [Abjad-Kids: An Arabic Speech Classification Dataset for Primary Education](https://mlsanity.com/paper/2603.20255/) (2026)
- [Child ASR Adaptation with Adult Retention: An Empirical Study](https://mlsanity.com/paper/2610.08827/) (2026)

## Abstract (arXiv)

Children speech recognition is challenging mainly due to the inherent high variability in children's physical and articulatory characteristics and expressions. This variability manifests in both acoustic constructs and linguistic usage due to the rapidly changing developmental stage in children's life. Part of the challenge is due to the lack of large amounts of available children speech data for efficient modeling. This work attempts to address the key challenges using transfer learning from adult's models to children's models in a Deep Neural Network (DNN) framework for children's Automatic Speech Recognition (ASR) task evaluating on multiple children's speech corpora with a large vocabulary. The paper presents a systematic and an extensive analysis of the proposed transfer learning technique considering the key factors affecting children's speech recognition from prior literature. Evaluations are presented on (i) comparisons of earlier GMM-HMM and the newer DNN Models, (ii) effectiveness of standard adaptation techniques versus transfer learning, (iii) various adaptation configurations in tackling the variabilities present in children speech, in terms of (a) acoustic spectral variability, and (b) pronunciation variability and linguistic constraints. Our Analysis spans over (i) number of DNN model parameters (for adaptation), (ii) amount of adaptation data, (iii) ages of children, (iv) age dependent-independent adaptation. Finally, we provide Recommendations on (i) the favorable strategies over various aforementioned - analyzed parameters, and (ii) potential future research directions and relevant challenges/problems persisting in DNN based ASR for children's speech.