TokenSynth uses a decoder-only transformer over audio tokens, conditioned on MIDI and CLAP timbre embeddings, to perform zero-shot instrument cloning, text-to-instrument synthesis, and text-guided timbre manipulation in one model.
Neural music instrument cloning from few samples,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
TokenSynth: A Token-based Neural Synthesizer for Instrument Cloning and Text-to-Instrument
TokenSynth uses a decoder-only transformer over audio tokens, conditioned on MIDI and CLAP timbre embeddings, to perform zero-shot instrument cloning, text-to-instrument synthesis, and text-guided timbre manipulation in one model.