On the Futility of Learning Complex Frame-Level Language Models for Chord Recognition

Korzeniowski F, Widmer G. On the Futility of Learning Complex Frame-Level Language Models for Chord Recognition. In: AES Conference: 2017 AES International Conference on Semantic Audio. Audio Engineering Society; 2017. Paper P2-6. Available from: https://aes.org/publications/elibrary-page/?id=18776

@inproceedings{Korzeniowski2017_18776,
  author = {Korzeniowski, Filip and Widmer, Gerhard},
  title = {{On the Futility of Learning Complex Frame-Level Language Models for Chord Recognition}},
  booktitle = {AES Conference: 2017 AES International Conference on Semantic Audio},
  note = {Paper P2-6},
  year = {2017},
  month = jun,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=18776}
}

TY  - CPAPER
TI  - On the Futility of Learning Complex Frame-Level Language Models for Chord Recognition
AU  - Korzeniowski, Filip
AU  - Widmer, Gerhard
T2  - AES Conference: 2017 AES International Conference on Semantic Audio
M1  - Paper P2-6
PY  - 2017
DA  - 2017/06/06
UR  - https://aes.org/publications/elibrary-page/?id=18776
PB  - Audio Engineering Society
LA  - en
AB  - Chord recognition systems use temporal models to post-process frame-wise chord predictions from acoustic models. Traditionally, first-order models such as Hidden Markov Models were used for this task, with recent works suggesting to apply Recurrent Neural Networks instead. In this paper, we argue that learning complex temporal models at the level of audio frames is futile on principle, and that non-Markovian models do not perform better than their first-order counterparts. We support our argument through experiments on the McGill Billboard dataset. We show that when learning complex temporal models at the frame level, improvements in chord sequence modelling are marginal and that these improvements do not translate when applied within a full chord recognition system.
ER  -