@inproceedings{d5bec719321e4f51884636a77fabd449,
title = "Learning optimal features for music transcription",
abstract = "This paper aims to design time-frequency representation (TFR) functions for automatic music transcription. It is desirable that the decomposition of those TFR functions are suitable for notes having variation of both pitch and spectral envelop over time. The Harmonic Adaptive Latent Component Analysis (HALCA) model adopted in this paper allows considering those two kinds of variations simultaneously. We evaluate the influence of three TFR functions including IIR, FIR filter bank semigram (FBSG) and constant-Q transform semigram in automatic music transcription task, on a database of popular and polyphonic classic music. The experiment results show that the filter bank based representations are suitable for multiple-instrument recordings and a CQT-based representation turns out to provide very accurate transcription for solo-instrument recordings.",
keywords = "constant-Q transform, filter bank, logarithmic compression, music transcription, Semigram features",
author = "Huaiping Ming and Dongyan Huang and Lei Xie and Haizhou Li",
note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 2nd IEEE China Summit and International Conference on Signal and Information Processing, IEEE ChinaSIP 2014 ; Conference date: 09-07-2014 Through 13-07-2014",
year = "2014",
month = sep,
day = "3",
doi = "10.1109/ChinaSIP.2014.6889211",
language = "英语",
series = "2014 IEEE China Summit and International Conference on Signal and Information Processing, IEEE ChinaSIP 2014 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "105--109",
booktitle = "2014 IEEE China Summit and International Conference on Signal and Information Processing, IEEE ChinaSIP 2014 - Proceedings",
}