5 papers
Fourier is Frontier: Frequency-Aware Autoencoding for High-Fidelity Music Reconstruction
Kangdi Wang, Yusheng Dai, Jin Xu
Continuous-latent audio autoencoders form the backbone of latent music generators, yet decoders at high compression rates commonly exhibit three failure modes: high-frequency loss,…
CineDub: Scaling End-to-End Video Dubbing to Multi-Speaker Dialogues with Coherent Sound Effects
Yusheng Dai, Kangdi Wang, Baolong Gao +4
Automatic video dubbing in the wild remains fundamentally limited by two competing constraints: hierarchical methods depend on brittle, multi-stage preprocessing pipelines that sev…
Qwen-Music Technical Report
Jin Xu, Kangdi Wang, Ruibin Yuan +24
We introduce Qwen-Music, a music generation model that produces high-fidelity songs with complete vocals. It supports text-to-music generation from descriptions, lyrics, and musica…
DuoTok: Source-Aware Dual-Track Music Tokenization for Vocal-Accompaniment Generation
Rui Lin, Zhiyue Wu, Jiahe Le +5
Multi-track music generation requires tokens that preserve acoustic fidelity, support sequence modeling, and maintain cross-track structure. Reconstruction-oriented codecs retain a…
Back to Ear: Perceptually Driven High Fidelity Music Reconstruction
Kangdi Wang, Zhiyue Wu, Dinghao Zhou +3
Variational Autoencoders (VAEs) are essential for large-scale audio tasks like diffusion-based generation. However, existing open-source models often neglect auditory perceptual as…