Developer Shows Singing Synthesis via Branching Vocal Tract Network

Developer jamesonhodge demos a singing synthesis model that models the vocal tract as a branching acoustic tube network instead of concatenating pitch-shifted phoneme recordings, with score conversion support; tuning against real singer recordings is ongoing and the timbre sounds impressive.

2026-11-08 ~ 2026-11-08 · 2 related posts

• Dev builds vocal synth modeling the vocal tract as branching acoustic tubes — mtizard · 2026-11-08
• Open-source vocal synth models vocal tract as acoustic tube network, adds MusicXML support — TinfoilTricorn · 2026-11-08