An evaluation of linear and non-linear models of expressive dynamics in classical piano and symphonic music

Abstract

Expressive interpretation forms an important but complex aspect of music, particularly in Western classical music. Modeling the relation between musical expression and structural aspects of the score being performed is an ongoing line of research. Prior work has shown that some simple numerical descriptors of the score (capturing dynamics annotations and pitch) are effective for predicting expressive dynamics in classical piano performances. Nevertheless, the features have only been tested in a very simple linear regression model. In this work, we explore the potential of non-linear and temporal modeling of expressive dynamics. Using a set of descriptors that capture different types of structure in the musical score, we compare linear and different non-linear models in a large-scale evaluation on three different corpora, involving both piano and orchestral music. To the best of our knowledge, this is the first study where models of musical expression are evaluated on both types of music. We show that, in addition to being more accurate, non-linear models describe interactions between numerical descriptors that linear models do not.

What were you expecting? Using Expectancy Features to Predict Expressive Performances of Classical Piano Music

“…The sensitivity analysis also found some evidence relating to well-known rules/guidelines for performance [3,4]. Future work may include the use of expectancy features in combination with larger sets of score descriptors (such as those in [5,1]), and derive expectancy features from deep probabilistic models trained directly on (polyphonic) piano-roll representations.…”

“…RNNs are a state-of-the-art family of neural architectures for modeling sequential data. Following [1,6], we use bidirectional RNNs as non-linear regression models to assess how well the features described above predict expressive dynamics and tempo. In this work, we use an architecture with a composite bidirectional hidden layer with 5 units, consisting of a forwards and backwards long short-term memory layer (LSTMs).…”

A Comprehensive Survey on Deep Music Generation: Multi-level Representations, Algorithms, Evaluations, and Future Directions

“…The other performance modeling method is to use probability models, such as hierarchical HMMs [38], dynamic Bayesian networks (DBNs) [39], conditional random fields (CRFs) [40], and switched Kalman filters [41]. Another kind of method is neural network, such as using feedforward neural networks (FFNNs) to predict expression parameters as functions of music score features [42], and utilizing RNN to model temporal dependencies between score features and expressive parameters [43]. In addition, Grachten et al [44] use assorted unsupervised learning techniques to learn features with which they then predict expressive dynamics.…”

An Interdisciplinary Review of Music Performance Analysis

“…Much of the recent research has been on generating expressive performances with or without a musical score as input. While the vast majority of this body of work has focused on piano performances (Cancino-Chacón and Grachten, 2016;Malik and Ek, 2017;Jeong et al, 2019;Jeong et al, 2019b,a;Oore et al,. 2020;Maezawa et al, 2019), there are a few studies focused on other instruments such as violin and flute (Wang and Yang, 2019).…”