- Automatic transcription of stuttered speech remains a challenge, even for modern end-to-end (E2E) automatic speech recognition (ASR) frameworks. Dysfluencies and fluency-shaping artifacts are often overlooked, resulting in non-verbatim transcriptions with limited clinical and research value. We propose a parameter-efficient adaptation method to decode dysfluencies
and fluency modifications as special tokens within transcriptions, evaluated on simulated (LibriStutter, English) and natural (KSoF, German) stuttered speech datasets. To mitigate ASR performance disparities and bias towards English, we introduce a multistep fine-tuning strategy with language-adaptive pretraining. Tokenization analysis further highlights the tokenizer’s Englishcentric bias, which poses challenges for improving performance
on German data. Our findings demonstrate the effectiveness of lightweight adaptation techniques for dysfluency-aware ASR while exposing key limitations in multilingual E2E systems.
