A Complex Autoencoder learns transformation-invariant magnitude representations from audio for state-of-the-art results in audio-to-score alignment and repeated section discovery.
Music pattern discovery with variable markov oracle: A unified ap- proach to symbolic and audio representations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Learning Complex Basis Functions for Invariant Representations of Audio
A Complex Autoencoder learns transformation-invariant magnitude representations from audio for state-of-the-art results in audio-to-score alignment and repeated section discovery.