Similarity-guided LLM augmentation of speech-like texts reduces prediction error for low cognitive scores on a Japanese clinical dataset while preserving performance on the majority group.
InProceedings of INTER- SPEECH 2022
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Can Large Language Models Imitate Human Speech for Clinical Assessment? LLM-Driven Data Augmentation for Cognitive Score Prediction
Similarity-guided LLM augmentation of speech-like texts reduces prediction error for low cognitive scores on a Japanese clinical dataset while preserving performance on the majority group.