4 Conclusion

Great strides have been made in the field of Music Information Retrieval pertaining to Automatic Music Transcription, resulting in satisfactory results for certain underlying tasks, namely onset detection and single pitch estimation. Nevertheless, most AMT problems remain open as researchers worldwide study and apply new concepts everyday.

In the scope of this project, we have explored well-established concepts of onset detection and single pitch estimation, and succeeded in obtaining satisfactory results. We have as well explored two different approaches of multi-pitch estimation and obtained relatively coherent results with Klapuri’s method, but unfortunally failed in applying Non-Negative Factorisation as we hoped.

As this is our second attempt in approaching AMT, we have been able to study closely core concepts of AMT, and deeply explore the core difficulty of AMT systems that is Multi-pitch Estimation. As research has lead us to studying several methods and approaches to this problem, we had to restrict the study to two algorithms that are robust, mathematically sound and appreciated by the MIR community.

I have held interest for this subject for quite some time, partly because I am a violinist myself but also because of my fondness of the employed mathematical principles. Most importantly, this project requires application of various mathematical notions as well as computer science skills hence serving as a demonstration of acquired knowledge throughout the Masters program. This open problem is more suited to a PhD thesis subject or as a full-time focus research, we have attempted to do as much as we could to accomplish with very little time.

References

Bello, J.P., and M. Sandler. 2003. “Phase-Based Note Onset Detection for Music Signals.” In 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP ’03)., 5:V–441. https://doi.org/10.1109/ICASSP.2003.1200001.

Benetos, Emmanouil, Simon Dixon, Dimitrios Giannoulis, Holger Kirchhoff, and Anssi Klapuri. 2013. “Automatic Music Transcription: Challenges and Future Directions.” Journal of Intelligent Information Systems 41 (December). https://doi.org/10.1007/s10844-013-0258-3.

Brossier, Paul M. 2006. Automatic Annotation of Musical Audio for Interactive Applications.

Cheveigné, Alain de, and Hideki Kawahara. 2002. “YIN, a Fundamental Frequency Estimator for Speech and Music.” The Journal of the Acoustical Society of America 111 (4): 1917–30. https://doi.org/10.1121/1.1458024.

Cont, Arshia. 2006. “Realtime Multiple Pitch Observation Using Sparse Non-Negative Constraints,” 6.

Duxbury, Chris, Juan Pablo Bello, Mike Davies, and Mark Sandler. 2003. “COMPLEX DOMAIN ONSET DETECTION FOR MUSICAL SIGNALS,” 4.

Feynman, Richard. 1965. “The Feynman Lectures on Physics Vol. I Ch. 47: Sound. The Wave Equation.” https://www.feynmanlectures.caltech.edu/I_47.html.

Klapuri, Anssi. 2006. “Multiple Fundamental Frequency Estimation by Summing Harmonic Amplitudes,” 6.

Lahat, M., Russell J. Niederjohn, and David A. Krubsack. 1987. “A Spectral Autocorrelation Method for Measurement of the Fundamental Frequency of Noise-Corrupted Speech.” IEEE Trans. Acoustics, Speech, and Signal Processing. https://doi.org/10.1109/TASSP.1987.1165224.

Masri, Paul, and Andrew Bateman. 1996. “Improved Modelling of Attack Transients in Music Analysis-Resynthesis,” 4.

Müller, Meinard. 2015. Fundamentals of Music Processing - Audio, Analysis, Algorithms, Applications. Springer. https://www.audiolabs-erlangen.de/fau/professor/mueller/bookFMP.

Ross, M., H. Shaffer, A. Cohen, R. Freudberg, and H. Manley. 1974. “Average Magnitude Difference Function Pitch Extractor.” IEEE Transactions on Acoustics, Speech, and Signal Processing 22 (5): 353–62. https://doi.org/10.1109/TASSP.1974.1162598.

Schroeder, Manfred R. 1968. “Period Histogram and Product Spectrum: New Methods for Fundamental-Frequency Measurement.” The Journal of the Acoustical Society of America. https://doi.org/10.1121/1.1910902.

Smaragdis, P., and J.C. Brown. 2003. “Non-Negative Matrix Factorization for Polyphonic Music Transcription.” In 2003 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (IEEE Cat. No.03TH8684), 177–80. New Paltz, NY, USA: IEEE. https://doi.org/10.1109/ASPAA.2003.1285860.

Wikipedia. 2020. “Nyquist–Shannon Sampling Theorem.” Wikipedia. https://en.wikipedia.org/w/index.php?title=Nyquist%E2%80%93Shannon_sampling_theorem&oldid=941933031.

Yeh, Chunghsin. 2008. “Multiple Fundamental Frequency Estimation of Polyphonic Recordings,” 153.