English

Mixture-of-Experts with Intermediate CTC Supervision for Accented Speech Recognition

Computation and Language 2026-02-03 v1 Artificial Intelligence

Abstract

Accented speech remains a persistent challenge for automatic speech recognition (ASR), as most models are trained on data dominated by a few high-resource English varieties, leading to substantial performance degradation for other accents. Accent-agnostic approaches improve robustness yet struggle with heavily accented or unseen varieties, while accent-specific methods rely on limited and often noisy labels. We introduce Moe-Ctc, a Mixture-of-Experts architecture with intermediate CTC supervision that jointly promotes expert specialization and generalization. During training, accent-aware routing encourages experts to capture accent-specific patterns, which gradually transitions to label-free routing for inference. Each expert is equipped with its own CTC head to align routing with transcription quality, and a routing-augmented loss further stabilizes optimization. Experiments on the Mcv-Accent benchmark demonstrate consistent gains across both seen and unseen accents in low- and high-resource conditions, achieving up to 29.3% relative WER reduction over strong FastConformer baselines.

Keywords

Cite

@article{arxiv.2602.01967,
  title  = {Mixture-of-Experts with Intermediate CTC Supervision for Accented Speech Recognition},
  author = {Wonjun Lee and Hyounghun Kim and Gary Geunbae Lee},
  journal= {arXiv preprint arXiv:2602.01967},
  year   = {2026}
}
R2 v1 2026-07-01T09:31:35.855Z