2 papers
eess.AS2026
Synthetic Data Domain Adaptation for ASR via LLM-based Text and Phonetic Respelling Augmentation
Natsuo Yamashita, Koichi Nagatsuka, Hiroaki Kokubo +2
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…
cs.CL2025
Model-free Speculative Decoding for Transformer-based ASR with Token Map Drafting
Tuan Vu Ho, Hiroaki Kokubo, Masaaki Yamamoto +1
End-to-end automatic speech recognition (ASR) systems based on transformer architectures, such as Whisper, offer high transcription accuracy and robustness. However, their autoregr…