Transcribing Debussy's Syrinx dynamics through Linguistic Description: The MUDELD algorithm

Ros, M. Blanca; Molina-Solana, Miguel; Delgado, Miguel; Fajardo, Waldo; Vila, Amparo

doi:10.1016/j.fss.2015.08.004

Cited by 2 publications

(1 citation statement)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Across the music excerpts sampled, the results showed a larger dynamic range from p to f , with an average change of 13.42dB, than from f to p, with an average change of 11.97dB. [32] proposed the MUDELD (MUsic Dynamics Extraction through Linguistic Description) algorithm, which uses linguistic description techniques to categorise dynamic labels of separate musical phrases into three levels designated as piano (p), mezzo (m), and forte (f ). The basic idea of this study was to extract loudness information from audio input by computing the Root Mean Square of the signal followed by normalisation so that the resulting values lie in [0, 1].…”

Section: Related Researchmentioning

confidence: 86%

Dynamics and relativity: Practical implications of dynamic markings in the score

Kosta

Bandtlow

Chew

2018

Journal of New Music Research

View full text Add to dashboard Cite

This article focuses on the meaning and practical manifestations of expressive markings in the music score, specifically those markings that correspond to loudness levels-such as p (piano), mf (mezzo forte), and ff (fortissimo). We present results showing how the absolute meanings of dynamic markings change, depending on the intended (score defined) and projected (actually performed) dynamic levels of the surrounding musical context. The analysis of recorded performances shows different realisations of the same dynamic markings throughout a recording of a piece of music. Reasons for this phenomenon include the score location of the markings, such as the beginning of a piece, and the marking's location in relation to that of previous ones. Observations show that more often than not, the transition between the two markings is more consistent when pianists move from a louder to a softer marking, or move between markings that both represent a high intensity, or when the markings show high levels of contrast. For markings that appear in the score more than twice, there tends to be significant difference in the ways they are interpreted in a recording. Finally we present evidence that pianists with high numbers of outlier recordings, i.e. showing uniqueness in the ways they transition between dynamic markings, tend to co-occur in outlier clusters for a significant number of Mazurkas, meaning they diverge from common practice in similar ways. Applications of these results include expression synthesis and music transcription.

show abstract

Section: Related Researchmentioning

confidence: 86%

Dynamics and relativity: Practical implications of dynamic markings in the score

Kosta

Bandtlow

Chew

2018

Journal of New Music Research

View full text Add to dashboard Cite

show abstract

Mapping between dynamic markings and performed loudness: a machine learning approach

Kosta

Ramírez

Bandtlow

et al. 2016

Journal of Mathematics and Music

View full text Add to dashboard Cite

Loudness variation is one of the foremost tools for expressivity in music performance. Loudness is frequently notated as dynamic markings such as p (piano, meaning soft) or f (forte, meaning loud). While dynamic markings in music scores are important indicators of how music pieces should be interpreted, their meaning is less straightforward than it may seem, and depends highly on the context in which they appear. In this article, we investigate the relationship between dynamic markings in the score and performed loudness by applying machine-learning techniques-decision trees, support vector machines, artificial neural networks, and a k-nearest neighbor method-to the prediction of loudness levels corresponding to dynamic markings, and to the classification of dynamic markings given loudness values. The methods are applied to forty-four recordings of performances of Chopin's Mazurkas each by eight pianists. The results show that loudness values and markings can be predicted relatively well when trained across recordings of the same piece, but fail dismally when trained across the pianist's recordings of other pieces, demonstrating that score features may trump individual style when modeling loudness choices. Evidence suggests that all the features chosen for the task are relevant, and analysis of the results reveal the forms (such as the return of the theme) and structures (such as dynamic marking repetitions) that influence predictability of loudness and markings. Modeling of loudness trends in expressive performance appears to be a delicate matter, and sometimes loudness expression can be a matter of the performer's idiosyncracy.

show abstract

Transcribing Debussy's Syrinx dynamics through Linguistic Description: The MUDELD algorithm

Cited by 2 publications

References 54 publications

Dynamics and relativity: Practical implications of dynamic markings in the score

Dynamics and relativity: Practical implications of dynamic markings in the score

Mapping between dynamic markings and performed loudness: a machine learning approach

Contact Info

Product

Resources

About