A LLaVA-style model with an added Whisper speech encoder answers spoken questions about images, trained on TTS-synthesized speech and reaching near the text-input baseline.
Visual question answering (VQA) attempts to describe, locate, and reason regarding some visual input [9, 10, 11]
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Spoken question answering for visual queries
A LLaVA-style model with an added Whisper speech encoder answers spoken questions about images, trained on TTS-synthesized speech and reaching near the text-input baseline.