works on
audio autoencoder 1fast encoding 1large-scale training 1low-bitrate compression 1text-to-audio generation 1transformer architecture 1

From the 1 of 13 linked papers with an AI index.

collaborators
Showing eess.ASShow all

1 paper · 1 filter

eess.AS2026

Qwen-Audio-VAE Technical Report

Ziyue Jiang, Dake Guo, Zekai Zhang +11

Qwen-Audio-VAE is a low‑bitrate, fast‑encoding continuous audio autoencoder that produces compact latent representations for scalable text‑to‑audio generation, using a causal encod…