We present AnyEdit, a unified, separation-free framework for speech and singing voice editing that preserves real-world acoustic environments, including noise, reverberation, and background music. Recent unified generative models already achieve strong speech and singing generation in clean conditions, but real-world v...
Yun-Jia Zhang, Ju-Nan Zhang, Jing Yang et al.· 0 citations
Experimental results demonstrate that BridgeCodec achieves superior wideband reconstruction and high perceptual quality, successfully bridging heavily bottlenecked, heterogeneous codecs.
Zi-Jian Lin, Jing Yang, Jin-Hao Luo et al.· 0 citations
Diff-Symbo is presented, an innovative method that uses latent diffusion model (LDM) to generate high-quality, diverse and long-duration symbolic music and improves the duration and the compositional consistency of music generation through an autoregressive approach.
Zhi-Wei Lin, Jun Chen, Bo-Shi Tang et al.· 0 citations
MIDI-to-Music system renders the melody and rhythm of a target MIDI sequence into musical segment while cloning instrument timbre from a prompt recording. Existing systems typically adopt one of two distinct paradigms: conditional generation with prompt audio alone, which remains applicable when aligned prompt MIDI is...
Chong Jing, Junan Zhang, Jing Yang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
