works on
autoencoder 1flow matching 1latent compression 1memory efficiency 1spoken dialog synthesis 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

eess.AS2026

ZipL-Dialog: Memory-Efficient Long-Form Spoken Dialog Synthesis via Latent Flow Matching

Jihwan Kim, Nam Soo Kim

The paper introduces ZipL-Dialog, a method that compresses mel-spectrograms into a low‑dimensional latent space and applies flow‑matching there, enabling memory‑efficient synthesis…