Context-Dependent Piano Music Transcription With Convolutional Sparse Coding
Abstract
This study presents a novel approach to automatic transcription of piano music in a context-dependent setting. This approach employs convolutional sparse coding to approximate the music waveform as the summation of piano note waveforms (dictionary elements) convolved with their temporal activations (onset transcription). The piano note waveforms are pre-recorded for the specific piano to be transcribed in the specific environment. During transcription, the note waveforms are fixed and their temporal activations are estimated and post-processed to obtain the pitch and onset transcription. This approach works in the time domain, models temporal evolution of piano notes, and estimates pitches and onsets simultaneously in the same framework. Finally, experiments show that it significantly outperforms a state-of-the-art music transcription method trained in the same context-dependent setting, in both transcription accuracy and time precision, in various scenarios including synthetic, anechoic, noisy, and reverberant environments.
- Authors:
-
- Univ. of Rochester, NY (United States). Dept. of Electrical and Computer Engineering
- Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
- Publication Date:
- Research Org.:
- Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 1457305
- Report Number(s):
- LA-UR-15-29587
Journal ID: ISSN 2329-9290
- Grant/Contract Number:
- AC52-06NA25396
- Resource Type:
- Accepted Manuscript
- Journal Name:
- IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Additional Journal Information:
- Journal Volume: 24; Journal Issue: 12; Journal ID: ISSN 2329-9290
- Publisher:
- IEEE - ACM
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 47 OTHER INSTRUMENTATION; automatic music transcription; piano transcription; reverberation; convolutional sparse coding
Citation Formats
Cogliati, Andrea, Duan, Zhiyao, and Wohlberg, Brendt. Context-Dependent Piano Music Transcription With Convolutional Sparse Coding. United States: N. p., 2016.
Web. doi:10.1109/TASLP.2016.2598305.
Cogliati, Andrea, Duan, Zhiyao, & Wohlberg, Brendt. Context-Dependent Piano Music Transcription With Convolutional Sparse Coding. United States. https://doi.org/10.1109/TASLP.2016.2598305
Cogliati, Andrea, Duan, Zhiyao, and Wohlberg, Brendt. Thu .
"Context-Dependent Piano Music Transcription With Convolutional Sparse Coding". United States. https://doi.org/10.1109/TASLP.2016.2598305. https://www.osti.gov/servlets/purl/1457305.
@article{osti_1457305,
title = {Context-Dependent Piano Music Transcription With Convolutional Sparse Coding},
author = {Cogliati, Andrea and Duan, Zhiyao and Wohlberg, Brendt},
abstractNote = {This study presents a novel approach to automatic transcription of piano music in a context-dependent setting. This approach employs convolutional sparse coding to approximate the music waveform as the summation of piano note waveforms (dictionary elements) convolved with their temporal activations (onset transcription). The piano note waveforms are pre-recorded for the specific piano to be transcribed in the specific environment. During transcription, the note waveforms are fixed and their temporal activations are estimated and post-processed to obtain the pitch and onset transcription. This approach works in the time domain, models temporal evolution of piano notes, and estimates pitches and onsets simultaneously in the same framework. Finally, experiments show that it significantly outperforms a state-of-the-art music transcription method trained in the same context-dependent setting, in both transcription accuracy and time precision, in various scenarios including synthetic, anechoic, noisy, and reverberant environments.},
doi = {10.1109/TASLP.2016.2598305},
journal = {IEEE/ACM Transactions on Audio, Speech, and Language Processing},
number = 12,
volume = 24,
place = {United States},
year = {Thu Aug 04 00:00:00 EDT 2016},
month = {Thu Aug 04 00:00:00 EDT 2016}
}
Web of Science
Works referencing / citing this record:
Deep learning-based automatic downbeat tracking: a brief review
journal, March 2019
- Jia, Bijue; Lv, Jiancheng; Liu, Dayiheng
- Multimedia Systems, Vol. 25, Issue 6