2019/04/02 by Aparna Balagopalan, Balagopalan, Aparna, Ksenia Shkaruta +3 · 1 citation
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Speech Recognition and Synthesis #Speech and dialogue systems
paper · pdf · doi:10.48550/arxiv.1904.01684
openalex publication_date 2019/04/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Automatic Speech Recognition (ASR) is a critical component of any\nfully-automated speech-based dementia detection model. However, despite years\nof speech recognition research, little is known about the impact of ASR\naccuracy on dementia detection. In this paper, we experiment with controlled\namounts of artificially generated ASR errors and investigate their influence on\ndementia detection. We find that deletion errors affect detection performance\nthe most, due to their impact on the features of syntactic complexity and\ndiscourse representation in speech. We show the trend to be generalisable\nacross two different datasets for cognitive impairment detection. As a\nconclusion, we propose optimising the ASR to reflect a higher penalty for\ndeletion errors in order to improve dementia detection performance.\n