5 papers
Diff-VS: Efficient Audio-Aware Diffusion U-Net for Vocals Separation
Yun-Ning, Hung, Richard Vogl +2
While diffusion models are best known for their performance in generative tasks, they have also been successfully applied to many other tasks, including audio source separation. Ho…
Timed text extraction from Taiwanese Kua-á-hì TV series
Tzu-Hung Huang, Yun-En Tsai, Yun-Ning Hung +3
Taiwanese opera (Kua-á-hì), a major form of local theatrical tradition, underwent extensive television adaptation notably by pioneers like Iûnn LÄ-hua. These videos, while pote…
Generating Separated Singing Vocals Using a Diffusion Model Conditioned on Music Mixtures
GenÃs Plaja-Roglans, Yun-Ning Hung, Xavier Serra +1
Separating the individual elements in a musical mixture is an essential process for music analysis and practice. While this is generally addressed using neural networks optimized t…
Efficient and Fast Generative-Based Singing Voice Separation using a Latent Diffusion Model
GenÃs Plaja-Roglans, Yun-Ning Hung, Xavier Serra +1
Extracting individual elements from music mixtures is a valuable tool for music production and practice. While neural networks optimized to mask or transform mixture spectrograms i…
Moises-Light: Resource-efficient Band-split U-Net For Music Source Separation
Yun-Ning, Hung, Igor Pereira +1
In recent years, significant advances have been made in music source separation, with model architectures such as dual-path modeling, band-split modules, or transformer layers achi…