Adding zero-shot synthetic audio from a text-to-speech system to text-only models improves cognitive-state prediction on seven tasks, though gains are small.
Title resolution pending
1 Pith paper cite this work, alongside 110 external citations. Polarity classification is still indexing.
1
Pith paper citing it
110
external citations · OpenAlex
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Synthetic Audio Helps for Cognitive State Tasks
Adding zero-shot synthetic audio from a text-to-speech system to text-only models improves cognitive-state prediction on seven tasks, though gains are small.