Reproduce “AutoSynth: Learning to Generate Editable Synthesizer Programs from Audio and Text” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Tristan Wu, Daniel Chin, Liwei Lin, Junan Zhang, Gus Xia
AutoSynth turns audio into editable synthesizer programs, combining MIDI performance, timbre settings, and modulation routes. For text prompts, frozen Stable Audio 3 generates an intermediate waveform for the program predictor. On a 128-example Gemini–Woosh inversion test, it records 0.37 CLAP cosine distance, versus 0.49 and 0.54 for systems using different synthesizers; the results concern short sounds and Helm.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.