ZipL-Dialog: Memory-Efficient Long-Form Spoken Dialog Synthesis via Latent Flow Matching
arXiv:2607.12496
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 of multi‑minute spoken dialogs without sacrificing naturalness.
Abstract
Zero-shot dialog TTS benefits from flow-matching, but minute-scale generation on dense mel-spectrograms causes severe memory bottlenecks, often forcing unnatural chunked synthesis. We propose ZipL-Dialog, which shifts conditional flow-matching into a 4x time-compressed (25 Hz) latent space. To preserve acoustic fidelity under compression, we employ a deterministic mel autoencoder with auxiliary mel-domain supervision and optimize the ZipFormer's hierarchical downsampling schedule. Experiments show that ZipL-Dialog reduces maximum peak GPU memory by 11.22x and accelerates inference by 2.23x over the baseline, substantially lowering the memory footprint of single-pass multi-minute dialog synthesis while maintaining perceptual naturalness.
Accepted to Interspeech 2026