论文信息 - MULTIPLE FUNDAMENTAL FREQUENCY ESTIMATION USING SPECTRAL STRUCTURE AND TEMPORAL EVOLUTION RULES

MULTIPLE FUNDAMENTAL FREQUENCY ESTIMATION USING SPECTRAL STRUCTURE AND TEMPORAL EVOLUTION RULES

This paper describes a method submitted for the MIREX 2010 Multiple Fundamental Frequency Estimation & Tracking Task 1, which uses pitch candidate selection rules employing spectral structure and temporal evolution. For preprocessing, the Resonator Time-Frequency Image of the input signal is employed as a time-frequency representation, a noise suppression model is used, and a spectral whitening procedure is performed. Also, tuning and inharmonicity parameters are extracted for the complete recording and a frame-by-frame pitch salience function is generated. Pitch presence tests are performed utilizing informa tion from the spectral structure of pitch candidates, aimin g to suppress errors occurring at multiples and sub-multiples of the true pitches. Additional tests for the estimation of harmonically related F0s are performed over time, based on the common amplitude modulation assumption.

S. Dixon | Emmanouil Benetos

[1] Juan Pablo,et al. Towards the automated analysis of simple polyphonic music : a knowledge-based approach , 2003 .

[2] Anssi Klapuri,et al. Multiple fundamental frequency estimation based on harmonicity and spectral smoothness , 2003, IEEE Trans. Speech Audio Process..

[3] Luis I. Ortiz-Berenguer,et al. PIANO TRANSCRIPTION USING PATTERN RECOGNITION: ASPECTS ON PARAMETER EXTRACTION , 2004 .

[4] Ruohua Zhou,et al. Feature extraction of musical content for automatic music transcription , 2006 .

[5] Dan Stowell,et al. Adaptive whitening for Improved Real-Time audio onset Detection , 2007, ICMC.

[6] DeLiang Wang,et al. Monaural Musical Sound Separation Based on Pitch and Common Amplitude Modulation , 2009, IEEE Transactions on Audio, Speech, and Language Processing.

[7] Anssi Klapuri. A Method for Visualizing the Pitch Content of Polyphonic Music Signals , 2009, ISMIR.

[8] Roland Badeau,et al. Multipitch Estimation of Piano Sounds Using a New Probabilistic Spectral Smoothness Principle , 2010, IEEE Transactions on Audio, Speech, and Language Processing.