A compact two-branch model with note-level contrastive clustering performs multi-instrument transcription and dynamic separation competitively while running efficiently on low-resource hardware.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Lightweight Two-Branch Architecture for Multi-Instrument Transcription via Note-Level Contrastive Clustering
A compact two-branch model with note-level contrastive clustering performs multi-instrument transcription and dynamic separation competitively while running efficiently on low-resource hardware.