Sage Journals: Discover world-class research

Abstract

German

Spanish

French

Italian

Measurable features of expressive piano performance include timing, dynamics, articulation and pedalling. This paper concerns the measurement of expressive timing and dynamics in audio recordings of piano music using a multi-stage semi-automated expression extraction process. A digitised version of the musical score is synchronised with the audio recording using a simple manual beat tapping system. The continuous wavelet transform (CWT) is then employed, with a Morlet wavelet, to correct the beat tapped times, and any further errors are then corrected manually. Precise note and chord onset times and dynamics of the recorded performance can then be calculated using the CWT. Sample results of the measurement of expression in keyboard music by Bach are given and the application of the algorithms to end users discussed.

Get full access to this article

View all access options for this article.

References

Binet

Courtier

(1895). Recherches graphiques sur la musique. L'Année Psycologique, 2, 201–22.

Cook

(2007). Performance analysis and Chopin's mazurkas. Musicae Scientiae, this issue.

Dixon

(2003). Towards automatic analysis of expressive performance. In Proceedings of the 5^th Triennial Conference of the European Society for the Cognitive Sciences of Music (ESCOM5), 107–10.

Dixon

(2005). An on-line time warping algorithm for tracking musical performances. In Proceedings of the International Joint Conference on Artificial Intelligence 2005, Edinburgh.

Drake

Penel

Bigand

(2000). Tapping in time with mechanically and expressively performed music. Music Perception, 18, 1–23.

Earis

(2006). The extraction of performance parameters from acoustic recordings of piano music. PhD thesis. Manchester, UK: University of Manchester.

Gabrielsson

(1999). Music Performance. In Deutsch

(ed), Psychology of Music (2^nd ed.), 501–602. San Diego: Academic Press.

Goto

(2001). An audio-based real-time beat tracking system for music with or without drum-sounds. Journal of New Music Research, 30, 159–71.

Klapuri

(1999). Sound onset detection by applying psychoacoustic knowledge. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing 1999.

10.

Klapuri

(2003). Automatic transcription of music. In Proceedings of the Stockholm Music Acoustics Conference 2003, Stockholm, Sweden.

11.

Marolt

(2001). SONIC: Transcription of polyphonic piano music with neural networks. In Proceedings of the workshop on current directions in computer music research 2001, Barcelona, Spain, 217-24.

12.

Palmer

(1996). On the assignment of structure in music performance. Music Perception, 14, 23–56.

13.

Raphael

(2003). Orchestral musical accompaniment from synthesised audio. In Proceedings of the International Computer Music Conference 2003, Singapore.

14.

Repp

B. H.

(1992). Diversity and commonality in music performance: An analysis of timing microstructure in Schumann's “Traumerei”. Journal of the Acoustical Society of America, 92, 2546–68.

15.

Repp

B. H.

(1998). A microcosm of musical expression I: Quantitative analysis of pianists' timing in the initial measures of Chopin's Etude in E major. Journal of the Acoustical Society of America, 104, 1085–100.

16.

Repp

B. H.

(1999). A microcosm of musical expression II: Quantitative analysis of pianists' dynamics in the initial measures of Chopin's Etude in E major. Journal of the Acoustical Society of America, 105, 1971–88.

17.

Rioul

Vetterlim

(1991). Wavelets and signal processing. IEEE Signal Processing Magazine, 8, 14–38.

18.

Scheirer

E. D.

(1996). Extracting expressive performance information from recorded audio. Machine Listening Group, MIT Media Laboratory.

19.

Seashore

C.E.

(1938). Psychology of Music, New York: McGraw-Hill.

20.

Todd

N. P. M.

(1992). The dynamics of dynamics: A model of musical expression. Journal of the Acoustical Society of America, 91, 3540–50.

21.

Widmer

(2005). Studying a creative act with computers: Music performance studies with automated performance methods. Musicae Scientiae, 9, 11–30.

An Algorithm to Extract Expressive Timing and Dynamics from Piano Recordings

Abstract

Get full access to this article

References