Pith. sign in

Towards human-like spoken dialogue generation between ai agents from written dialogue

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

1 Pith paper citing it

fields

eess.AS 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching

eess.AS · 2025-07-12 · conditional · novelty 6.0

ZipVoice-Dialog is a flow-matching non-autoregressive model for zero-shot spoken dialogue generation that uses curriculum learning and speaker-turn embeddings, paired with a new 6.8k-hour OpenDialog dataset, and reports better speed and quality than autoregressive baselines.

citing papers explorer

Showing 1 of 1 citing paper.

  • ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching eess.AS · 2025-07-12 · conditional · none · ref 20

    ZipVoice-Dialog is a flow-matching non-autoregressive model for zero-shot spoken dialogue generation that uses curriculum learning and speaker-turn embeddings, paired with a new 6.8k-hour OpenDialog dataset, and reports better speed and quality than autoregressive baselines.