Pith. sign in

Title resolution pending

We demonstrate the practical use of a zero-shot multi-speaker TTS system to synthesize QAs, overcoming previous challenges, preventing training-test speaker leakage

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
browse 1 citing papers

Title metadata for this work has not finished resolving. The hub is built from the citation graph; the title resolver retries DOI and OpenAlex on its next pass.

fields

eess.AS 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Spoken question answering for visual queries

eess.AS · 2025-05-29 · conditional · novelty 6.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • Spoken question answering for visual queries eess.AS · 2025-05-29 · conditional · none · ref 4

    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.