CHSER: A Dataset and Case Study on Generative Speech Error Correction for Child ASR

2025/05/24 by Natarajan Balaji Shankar, Shankar, Natarajan Balaji, Kaiyuan Zhang +6 · 1 citation
Computer Science · #Audio and Speech Processing (eess.AS) #FOS: Electrical engineering #Speech Recognition and Synthesis #Speech and Audio Processing #Speech and dialogue systems #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2505.18463

openalex publication_date 2025/05/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Automatic Speech Recognition (ASR) systems struggle with child speech due to its distinct acoustic and linguistic variability and limited availability of child speech datasets, leading to high transcription error rates. While ASR error correction (AEC) methods have improved adult speech transcription, their effectiveness on child speech remains largely unexplored. To address this, we introduce CHSER, a Generative Speech Error Correction (GenSEC) dataset for child speech, comprising 200K hypothesis-transcription pairs spanning diverse age groups and speaking styles. Results demonstrate that fine-tuning on the CHSER dataset achieves up to a 28.5% relative WER reduction in a zero-shot setting and a 13.3% reduction when applied to fine-tuned ASR systems. Additionally, our error analysis reveals that while GenSEC improves substitution and deletion errors, it struggles with insertions and child-specific disfluencies. These findings highlight the potential of GenSEC for improving child ASR.

Citations

• NeKo: Cross-Modality Post-Recognition Error Correction with Tasks-Guided Mixture-of-Experts Language Model
• GPT-4o System Card
• Failing Forward: Improving Generative Error Correction for ASR with Synthetic Data and Retrieval Augmentation
• ASR Error Correction using Large Language Models
• Benchmarking Children's ASR with Supervised and Self-supervised Speech Foundation Models
• Large Language Models are Efficient Learners of Noise-Robust Speech Recognition
• Automatic Disfluency Detection from Untranscribed Speech
• Whispering LLaMA: A Cross-Modal Generative Error Correction Framework for Speech Recognition
• HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models
• My Science Tutor (MyST) -- A Large Corpus of Children's Conversational Speech
• Kid-Whisper: Towards Bridging the Performance Gap in Automatic Speech Recognition for Children VS. Adults
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• Robust Speech Recognition via Large-Scale Weak Supervision
• Scaling Instruction-Finetuned Language Models
• Cross-Modal ASR Post-Processing System for Error Correction and Utterance Rejection
• An Explanation of In-context Learning as Implicit Bayesian Inference
• WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing
• LoRA: Low-Rank Adaptation of Large Language Models
• HuBERT: Self-Supervised Speech Representation Learning by Masked\n Prediction of Hidden Units
• wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
• Improving Readability for Automatic Speech Recognition Transcription
• ASR Error Correction and Domain Adaptation Using Machine Translation
• Quantization and Training of Neural Networks for Efficient\n Integer-Arithmetic-Only Inference
• Estimation of probabilities from sparse data for the language model component of a speech recognizer

Cited by

• Can large audio language models understand child stuttering speech? speech summarization, and source separation

Related

• Large Language Models based ASR Error Correction for Child Conversations
• Causal Analysis of ASR Errors for Children: Quantifying the Impact of Physiological, Cognitive, and Extrinsic Factors
• Causal Structure Discovery for Error Diagnostics of Children's ASR
• A Survey on Non-Intrusive ASR Refinement: From Output-Level Correction to Full-Model Distillation
• Failing Forward: Improving Generative Error Correction for ASR with Synthetic Data and Retrieval Augmentation