Multipitch estimation of piano sounds using a new probabilistic spectral smoothness principle

Authors:
Valentin Emiya;Roland Badeau;Bertrand David
Affiliations:
INRIA, Centre lnria Rennes--Bretagne Atlantique, Rennes, France and Institut Télécom, Télécom ParisTech, CNRS, LTCI, Paris, France;Institut Télécom, Télécom ParisTech, CNRS, LTCI, Paris, France;Institut Télécom, Télécom ParisTech, CNRS, LTCI, Paris, France
Venue:
IEEE Transactions on Audio, Speech, and Language Processing
Year:
2010

Citing 9
Cited 2

Extrapolation, Interpolation, and Smoothing of Stationary Time Series

Extrapolation, Interpolation, and Smoothing of Stationary Time Series
Signal Processing Methods for Music Transcription

Signal Processing Methods for Music Transcription
A discriminative model for polyphonic piano transcription

EURASIP Journal on Applied Signal Processing
Expectation-maximization algorithm for multi-pitch estimation and separation of overlapping harmonic spectra

ICASSP '09 Proceedings of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing
Multi-Pitch Estimation

Multi-Pitch Estimation
A Multipitch Analyzer Based on Harmonic Temporal Structured Clustering

IEEE Transactions on Audio, Speech, and Language Processing
A generative model for music transcription

IEEE Transactions on Audio, Speech, and Language Processing
Automatic Piano Transcription Using Frequency and Time-Domain Information

IEEE Transactions on Audio, Speech, and Language Processing
A connectionist approach to automatic transcription of polyphonic piano music

IEEE Transactions on Multimedia

Temporally-Constrained convolutive probabilistic latent component analysis for multi-pitch detection

LVA/ICA'12 Proceedings of the 10th international conference on Latent Variable Analysis and Signal Separation
Automatic music transcription: challenges and future directions

Journal of Intelligent Information Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

A new method for the estimation of multiple concurrent pitches in piano recordings is presented. It addresses the issue of overlapping overtones by modeling the spectral envelope of the overtones of each note with a smooth autoregressive model. For the background noise, a moving-average model is used and the combination of both tends to eliminate harmonic and subharmonic erroneous pitch estimations. This leads to a complete generative spectral model for simultaneous piano notes, which also explicitly includes the typical deviation from exact harmonicity in a piano overtone series. The pitch set which maximizes an approximate likelihood is selected from among a restricted number of possible pitch combinations as the one. Tests have been conducted on a large homemade database called MAPS, composed of piano recordings from a real upright piano and from high-quality samples.