TY - GEN
T1 - Large vocabulary automatic chord estimation with an even chance training scheme
AU - Deng, Junqi
AU - Kwok, Yu Kwong
N1 - Publisher Copyright:
© 2019 Junqi Deng and Yu-Kwong Kwok.
PY - 2017
Y1 - 2017
N2 - This paper presents a large vocabulary automatic chord estimation system implemented using a bidirectional long short-term memory recurrent neural network trained with a skewed-class-aware scheme. This scheme gives the uncommon chord types much more exposure during the training process. The evaluation results indicate that: compared with a normal training scheme, the proposed scheme can boost the weighted chord symbol recalls of some uncommon chords and significantly improve the average chord quality accuracy, at the expense of the overall weighted chord symbol recall.
AB - This paper presents a large vocabulary automatic chord estimation system implemented using a bidirectional long short-term memory recurrent neural network trained with a skewed-class-aware scheme. This scheme gives the uncommon chord types much more exposure during the training process. The evaluation results indicate that: compared with a normal training scheme, the proposed scheme can boost the weighted chord symbol recalls of some uncommon chords and significantly improve the average chord quality accuracy, at the expense of the overall weighted chord symbol recall.
UR - https://www.scopus.com/pages/publications/85057936249
M3 - Conference contribution
AN - SCOPUS:85057936249
T3 - Proceedings of the 18th International Society for Music Information Retrieval Conference, ISMIR 2017
SP - 531
EP - 536
BT - Proceedings of the 18th International Society for Music Information Retrieval Conference, ISMIR 2017
A2 - Cunningham, Sally Jo
A2 - Duan, Zhiyao
A2 - Hu, Xiao
A2 - Turnbull, Douglas
T2 - 18th International Society for Music Information Retrieval Conference, ISMIR 2017
Y2 - 23 October 2017 through 27 October 2017
ER -