The analysis of ASR errors in BERT-based Alzheimer's detection shows that stopwords dominate the errors but barely affect classification, while task-related keywords are transcribed accurately and are the decisive factor.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Not All Errors Are Equal: Investigation of Speech Recognition Errors in Alzheimer's Disease Detection
The analysis of ASR errors in BERT-based Alzheimer's detection shows that stopwords dominate the errors but barely affect classification, while task-related keywords are transcribed accurately and are the decisive factor.