Real-time F0 Estimation of Melody and Bass Lines in Musical Audio Signals

F0 Display

This project is proposed and researched by Masataka Goto.

Japanese version is here.
Japanese version


We have developed a robust method for estimating the fundamental frequency (F0) of melody and bass lines in monaural real-world musical audio signals containing sounds of various instruments. Most previous F0-estimation methods had great difficulty dealing with such complex audio signals because they were designed to deal with mixtures of only a few sounds. To make it possible to estimate the F0 of the melody and bass lines, we propose a predominant-F0 estimation method called PreFEst that does not rely on the F0's unreliable frequency component and obtains the most predominant F0 supported by harmonics within an intentionally limited frequency range. It evaluates the relative dominance of every possible F0 by using the Expectation-Maximization algorithm and considers the temporal continuity of F0s by using a multiple-agent architecture. Experimental results show that our real-time system can detect the melody and bass lines in audio signals sampled from commercially distributed compact discs.


References:

  1. Masataka Goto: A Real-time Music Scene Description System: Predominant-F0 Estimation for Detecting Melody and Bass Lines in Real-world Audio Signals, Speech Communication (ISCA Journal), Vol.43, No.4, pp.311-329, September 2004.
    PDF
  2. Masataka Goto: A Predominant-F0 Estimation Method for Polyphonic Musical Audio Signals, Proceedings of the 18th International Congress on Acoustics (ICA 2004), pp.II-1085-1088, April 2004. (Invited Paper)
    PDF
  3. Masataka Goto, A Predominant-F0 Estimation Method for Real-world Musical Audio Signals: MAP Estimation for Incorporating Prior Knowledge about F0s and Tone Models, Proceedings of CRAC-2001 (Workshop on Consistent & Reliable Acoustic Cues for Sound Analysis), September 2001.
    PDF
  4. Masataka Goto: A Predominant-F0 Estimation Method for CD Recordings: MAP Estimation using EM Algorithm for Adaptive Tone Models, Proceedings of the 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2001), pp.V-3365-3368, May 2001.
    PDF
  5. Masataka Goto: F0 Estimation of Melody and Bass Lines in Musical Audio Signals, The Transactions of the Institute of Electronics, Information and Communication Engineers D-II, Vol.J84-D-II, No.1, pp.12-22, January 2001. (in Japanese)
  6. Masataka Goto: A Real-time Music Scene Description System: System Overview and Extension of F0 Estimation Method, Information Processing Society of Japan SIG Notes, 2000-MUS-37-2, Vol.2000, No.94, pp.9-16, October 2000 (in Japanese).
  7. Masataka Goto: A Robust Predominant-F0 Estimation Method for Real-time Detection of Melody and Bass Lines in CD Recordings, Proceedings of the 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2000), pp.II-757-760, June 2000.
    PDF
  8. Masataka Goto: Music Scene Description: A Predominant-F0 Estimation Method for Detecting Melody and Bass Lines, Proceedings of the Seventh Meeting of Special Interest Group on AI Challenges, SIG-Challenge-9907-8, pp.45-52, November 1999.
  9. Masataka Goto and Satoru Hayamizu: A Real-time Music Scene Description System: Detecting Melody and Bass Lines in Audio Signals, Working Notes of the IJCAI-99 Workshop on Computational Auditory Scene Analysis, pp.31-40, August 1999.
    PDF
  10. Masataka Goto: F0 Estimation of Melody and Bass Lines in Real-world Musical Audio Signals, Information Processing Society of Japan SIG Notes, 99-MUS-31-16, Vol.99, No.68, August 1999 (in Japanese).
    PDF


Back to:


Please E-mail comments and questions to
Masataka GOTO <m.goto [at] aist.go.jp>

All pages are copyrighted by the author. Unauthorized reproduction is strictly prohibited.
last update: May 11, 2000