6 papers
Efficient Vocal Source Separation Through Windowed Sink Attention
Christodoulos Benetatos, Yongyi Zang, Randal Leistikow
State-of-the-art vocal separation models like Mel-Band-Roformer rely on full temporal self-attention mechanisms, where each temporal frame interacts with every other frames. This i…
PromptReverb: Multimodal Room Impulse Response Generation Through Latent Rectified Flow Matching
Ali Vosoughi, Yongyi Zang, Qihui Yang +3
Room impulse response (RIR) generation remains a critical challenge for creating immersive virtual acoustic environments. Current methods suffer from two fundamental limitations: t…
Learning Interpretable Features in Audio Latent Spaces via Sparse Autoencoders
Nathan Paek, Yongyi Zang, Qihui Yang +1
While sparse autoencoders (SAEs) successfully extract interpretable features from language models, applying them to audio generation faces unique challenges: audio's dense nature r…
StylePitcher: Generating Style-Following and Expressive Pitch Curves for Versatile Singing Tasks
Jingyue Huang, Qihui Yang, Fei Yueh Chen +4
Existing pitch curve generators face two main challenges: they often neglect singer-specific expressiveness, reducing their ability to capture individual singing styles. And they a…
FlowSynth: Instrument Generation Through Distributional Flow Matching and Test-Time Search
Qihui Yang, Randal Leistikow, Yongyi Zang
Virtual instrument generation requires maintaining consistent timbre across different pitches and velocities, a challenge that existing note-level models struggle to address. We pr…
Smule Renaissance Small: Efficient General-Purpose Vocal Restoration
Yongyi Zang, Chris Manchester, David Young +9
Vocal recordings on consumer devices commonly suffer from multiple concurrent degradations: noise, reverberation, band-limiting, and clipping. We present Smule Renaissance Small (S…