English

Synthetic Data Domain Adaptation for ASR via LLM-based Text and Phonetic Respelling Augmentation

Audio and Speech Processing 2026-03-19 v1 Sound

Abstract

End-to-end automatic speech recognition often degrades on domain-specific data due to scarce in-domain resources. We propose a synthetic-data-based domain adaptation framework with two contributions: (1) a large language model (LLM)-based text augmentation pipeline with a filtering strategy that balances lexical diversity, perplexity, and domain-term coverage, and (2) phonetic respelling augmentation (PRA), a novel method that introduces pronunciation variability through LLM-generated orthographic pseudo-spellings. Unlike conventional acoustic-level methods such as SpecAugment, PRA provides phonetic diversity before speech synthesis, enabling synthetic speech to better approximate real-world variability. Experimental results across four domain-specific datasets demonstrate consistent reductions in word error rate, confirming that combining domain-specific lexical coverage with realistic pronunciation variation significantly improves ASR robustness.

Keywords

Cite

@article{arxiv.2603.16920,
  title  = {Synthetic Data Domain Adaptation for ASR via LLM-based Text and Phonetic Respelling Augmentation},
  author = {Natsuo Yamashita and Koichi Nagatsuka and Hiroaki Kokubo and Kota Dohi and Tuan Vu Ho},
  journal= {arXiv preprint arXiv:2603.16920},
  year   = {2026}
}

Comments

accepted by ICASSP 2026