Monophonic constrained non-negative sparse coding using instrument models for audio separation and transcription of monophonic source-based polyphonic mixtures

In this paper we propose a monophonic constrained signal decomposition model applied to polyphonic signals composed of several monophonic sources from different musical instruments. The harmonic constraint is particularly effective for tonal instruments because each note is associated with a unique...

Full description

Saved in:
Bibliographic Details
Published in:Multimedia tools and applications Vol. 72; no. 1; pp. 925 - 949
Main Authors: Rodríguez-Serrano, Francisco José, Carabias-Orti, Julio José, Vera-Candeas, Pedro, Canadas-Quesada, Francisco Jesús, Ruiz-Reyes, Nicolás
Format: Journal Article
Language:English
Published: Boston Springer US 01.09.2014
Springer
Springer Nature B.V
Subjects:
Acoustic signal processing
Acoustics
Analysis
Applied sciences
Audio signals
Computer Communication Networks
Computer Science
Constraints
Data Structures and Information Theory
Decomposition
Detection, estimation, filtering, equalization, prediction
Exact sciences and technology
Factorization
Fundamental areas of phenomenology (including applications)
Gain
Harmonics
Harmony (Music)
Information, signal and communications theory
Methods
Multimedia
Multimedia computer applications
Multimedia Information Systems
Music
Musical instruments
Physics
Sensors
Separation
Signal and communications theory
Signal processing
Signal, noise
Sound
Sound sources
Sparsity
Special Purpose and Application-Based Systems
Studies
Telecommunications and information theory
Transduction; acoustical devices for the generation and reproduction of sound
Source separation
Sparsity
Monophony
Non-negative matrix factorization (NMF)
Sparse representations
Non-negative sparse coding (NNSC)
Spectral analysis
Harmonicity
Music transcription
Harmonic
Acoustic signal
Audiofrequency
Matrix factorization
Sparse coding
Modeling
Separation method
Non negative matrix
Audio signal
Musical acoustics
Signal processing
Audio acoustics
Sparse representation
Pitch(acoustics)
Deterministic approach
ISSN:1380-7501, 1573-7721
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper we propose a monophonic constrained signal decomposition model applied to polyphonic signals composed of several monophonic sources from different musical instruments. The harmonic constraint is particularly effective for tonal instruments because each note is associated with a unique basis. The monophonic constraint is implemented by enforcing single-non-zero gains per instrument in the factorization process. The proposed method uses previously trained instrument models with a supervised procedure. Both constraints (harmonic and monophonic) are implemented in a deterministic manner. The proposed method has been tested for two audio signal applications, Sound Source Separation and Automatic Music Transcription. Comparison with other state-of-the-art methods using a dataset of polyphonic mixtures composed of monophonic sources has produced competitive and promising results.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1380-7501
1573-7721
DOI:10.1007/s11042-013-1398-8