Adapting Foundation Speech Recognition Models to Impaired Speech: A Semantic Re-chaining Approach for Personalization of German Speech
This work addresses communication barriers for individuals with atypical speech patterns, but it is incremental as it builds on existing models with a specific adaptation method.
The paper tackled the problem of adapting foundation speech recognition models to impaired speech by proposing a lightweight pipeline for personalization, showing promising improvements in transcription quality for a child with a structural speech impairment.
Speech impairments caused by conditions such as cerebral palsy or genetic disorders pose significant challenges for automatic speech recognition (ASR) systems. Despite recent advances, ASR models like Whisper struggle with non-normative speech due to limited training data and the difficulty of collecting and annotating non-normative speech samples. In this work, we propose a practical and lightweight pipeline to personalize ASR models, formalizing the selection of words and enriching a small, speech-impaired dataset with semantic coherence. Applied to data from a child with a structural speech impairment, our approach shows promising improvements in transcription quality, demonstrating the potential to reduce communication barriers for individuals with atypical speech patterns.