A segment-level auto-regressive sequence model for chord recognition reduces oversegmentation and improves performance on complex infrequent chords.
Experimental Setups Data.We use the dataset as BTC[3], consisting of 471 pop songs with manually aligned audio and chord annotations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
An event-based sequence modeling approach to recognizing non-triad chords with oversegmentation minimization
A segment-level auto-regressive sequence model for chord recognition reduces oversegmentation and improves performance on complex infrequent chords.