Continuous Learning for Children's ASR: Overcoming Catastrophic Forgetting with Elastic Weight Consolidation and Synaptic Intelligence

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ahadzi, Edem, Singh, Vishwanath Pratap, Kinnunen, Tomi, Hautamaki, Ville
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914074387808256
author Ahadzi, Edem
Singh, Vishwanath Pratap
Kinnunen, Tomi
Hautamaki, Ville
author_facet Ahadzi, Edem
Singh, Vishwanath Pratap
Kinnunen, Tomi
Hautamaki, Ville
contents In this work, we present the first study addressing automatic speech recognition (ASR) for children in an online learning setting. This is particularly important for both child-centric applications and the privacy protection of minors, where training models with sequentially arriving data is critical. The conventional approach of model fine-tuning often suffers from catastrophic forgetting. To tackle this issue, we explore two established techniques: elastic weight consolidation (EWC) and synaptic intelligence (SI). Using a custom protocol on the MyST corpus, tailored to the online learning setting, we achieve relative word error rate (WER) reductions of 5.21% with EWC and 4.36% with SI, compared to the fine-tuning baseline.
format Preprint
id arxiv_https___arxiv_org_abs_2505_20216
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Continuous Learning for Children's ASR: Overcoming Catastrophic Forgetting with Elastic Weight Consolidation and Synaptic Intelligence
Ahadzi, Edem
Singh, Vishwanath Pratap
Kinnunen, Tomi
Hautamaki, Ville
Audio and Speech Processing
In this work, we present the first study addressing automatic speech recognition (ASR) for children in an online learning setting. This is particularly important for both child-centric applications and the privacy protection of minors, where training models with sequentially arriving data is critical. The conventional approach of model fine-tuning often suffers from catastrophic forgetting. To tackle this issue, we explore two established techniques: elastic weight consolidation (EWC) and synaptic intelligence (SI). Using a custom protocol on the MyST corpus, tailored to the online learning setting, we achieve relative word error rate (WER) reductions of 5.21% with EWC and 4.36% with SI, compared to the fine-tuning baseline.
title Continuous Learning for Children's ASR: Overcoming Catastrophic Forgetting with Elastic Weight Consolidation and Synaptic Intelligence
topic Audio and Speech Processing
url https://arxiv.org/abs/2505.20216