Carlos Cancino-Chacón

German Barquero, Nadine Bertsch, Manojkumar Marramreddy et al.

In extended reality (XR), generating full-body motion of the users is important to understand their actions, drive their virtual avatars for social interaction, and convey a realistic sense of presence. While prior works focused on spatially sparse and always-on input signals from motion controllers, many XR applications opt for vision-based hand tracking for reduced user friction and better immersion. Compared to controllers, hand tracking signals are less accurate and can even be missing for an extended period of time. To handle such unreliable inputs, we present Rolling Prediction Model (RPM), an online and real-time approach that generates smooth full-body motion from temporally and spatially sparse input signals. Our model generates 1) accurate motion that matches the inputs (i.e., tracking mode) and 2) plausible motion when inputs are missing (i.e., synthesis mode). More importantly, RPM generates seamless transitions from tracking to synthesis, and vice versa. To demonstrate the practical importance of handling noisy and missing inputs, we present GORP, the first dataset of realistic sparse inputs from a commercial virtual reality (VR) headset with paired high quality body motion ground truth. GORP provides >14 hours of VR gameplay data from 28 people using motion controllers (spatially sparse) and hand tracking (spatially and temporally sparse). We benchmark RPM against the state of the art on both synthetic data and GORP to highlight how we can bridge the gap for real-world applications with a realistic dataset and by handling unreliable input signals. Our code, pretrained models, and GORP dataset are available in the project webpage.

Maarten Grachten, Carlos Cancino-Chacón, Thassilo Gadermaier

This demo paper introduces partitura, a Python package for handling symbolic musical information. The principal aim of this package is to handle richly structured musical information as conveyed by modern staff music notation. It provides a much wider range of possibilities to deal with music than the more reductive (but very common) piano roll-oriented approach inspired by the MIDI standard. The package is an open source project and is available on GitHub.

Suhit Chiruthapudi, Adam Štefunko, Silvan Peter et al.

Symbolic music alignment links notes in a symbolic performance to their counterparts in a score. While existing alignment encoding formats provide unique correspondences between these notes, there are various musical practices and forms such as practice repetitions in rehearsal and improvised realizations in basso continuo that require a more flexible approach to encoding their alignments. In this paper, we propose a minimal, backward-compatible extension to the Match file format to support such non-unique and semantically complex alignments. We introduce two virtual pointer notes - virtual score notes and virtual performance notes - which allow to encode multiple links between performance and score notes. In addition we expand the Match file's 'section' line to include semantically meaningful annotations of performance regions beyond score-indicated musical repetitions. We further demonstrate the utility of these extensions through two representative use-cases in piano rehearsal and basso continuo.

Silvan David Peter, Shreyan Chowdhury, Carlos Eduardo Cancino-Chacón et al.

Semantic embeddings play a crucial role in natural language-based information retrieval. Embedding models represent words and contexts as vectors whose spatial configuration is derived from the distribution of words in large text corpora. While such representations are generally very powerful, they might fail to account for fine-grained domain-specific nuances. In this article, we investigate this uncertainty for the domain of characterizations of expressive piano performance. Using a music research dataset of free text performance characterizations and a follow-up study sorting the annotations into clusters, we derive a ground truth for a domain-specific semantic similarity structure. We test five embedding models and their similarity structure for correspondence with the ground truth. We further assess the effects of contextualizing prompts, hubness reduction, cross-modal similarity, and k-means clustering. The quality of embedding models shows great variability with respect to this task; more general models perform better than domain-adapted ones and the best model configurations reach human-level agreement.

Laura Bishop, Carlos Cancino-Chacón, Werner Goebl

In this chapter, we focus on two main categories of visual interaction: body gestures and gaze direction. Our focus on body gestures is motivated by research showing that gesture patterns often change during joint action tasks to become more predictable (van der Wel et al., 2016). Moreover, coordination sometimes emerges between musicians at the level of body sway (Chang et al., 2017). Our focus on gaze direction was motivated by the fact that gaze can serve simultaneously as a means of obtaining information about the world and as a means of communicating one's own attention and intent.

Carlos Cancino-Chacón, Silvan Peter, Shreyan Chowdhury et al.

A piece of music can be expressively performed, or interpreted, in a variety of ways. With the help of an online questionnaire, the Con Espressione Game, we collected some 1,500 descriptions of expressive character relating to 45 performances of 9 excerpts from classical piano pieces, played by different famous pianists. More specifically, listeners were asked to describe, using freely chosen words (preferably: adjectives), how they perceive the expressive character of the different performances. In this paper, we offer a first account of this new data resource for expressive performance research, and provide an exploratory analysis, addressing three main questions: (1) how similarly do different listeners describe a performance of a piece? (2) what are the main dimensions (or axes) for expressive character emerging from this?; and (3) how do measurable parameters of a performance (e.g., tempo, dynamics) and mid- and high-level features that can be predicted by machine learning models (e.g., articulation, arousal) relate to these expressive dimensions? The dataset that we publish along with this paper was enriched by adding hand-corrected score-to-performance alignments, as well as descriptive audio features such as tempo and dynamics curves.

Olivier Lartillot, Carlos Cancino-Chacón, Charles Brazier

We present a new system for real-time visualisation of music performance, focused for the moment on a fugue played by a string quartet. The basic principle is to offer a visual guide to better understand music using strategies that should be as engaging, accessible and effective as possible. The pitch curves related to the separate voices are drawn on a space whose temporal axis is normalised with respect to metrical positions, and aligned vertically with respect to their thematic and motivic classification. Aspects related to tonality are represented as well. We describe the underlying technologies we have developed and the technical setting. In particular, the rhythmical and structural representation of the piece relies on real-time polyphonic audio-to-score alignment using online dynamic time warping. The visualisation will be presented at a concert of the Danish String Quartet, performing the last piece of The Art of Fugue by Johann Sebastian Bach.

Laura Bishop, Carlos Cancino-Chacón, Werner Goebl

Skilled ensemble musicians coordinate with high precision, even when improvising or interpreting loosely-defined notation. Successful coordination is supported primarily through shared attention to the musical output; however, musicians also interact visually, particularly when the musical timing is irregular. This study investigated the performance conditions that encourage visual signalling and interaction between ensemble members. Piano and clarinet duos rehearsed a new piece as their body motion was recorded. Analyses of head movement showed that performers communicated gesturally following held notes. Gesture patterns became more consistent as duos rehearsed, though consistency dropped again during a final performance given under no-visual-contact conditions. Movements were smoother and interperformer coordination was stronger during irregularly-timed passages than elsewhere in the piece, suggesting heightened visual interaction. Performers moved more after rehearsing than before, and more when they could see each other than when visual contact was occluded. Periods of temporal instability and increased familiarity with the music and co-performer seem to encourage visual interaction, while specific communicative gestures are integrated into performance routines through rehearsal. We propose that visual interaction may support successful ensemble performance by affirming coordination throughout periods of temporal instability and serving as a social motivator to promote creative risk-taking.

Zhengshan Shi, Carlos Cancino-Chacón, Gerhard Widmer

Musicians produce individualized, expressive performances by manipulating parameters such as dynamics, tempo and articulation. This manipulation of expressive parameters is informed by elements of score information such as pitch, meter, and tempo and dynamics markings (among others). In this paper we present an interactive interface that gives users the opportunity to explore the relationship between structural elements of a score and expressive parameters. This interface draws on the basis function models, a data-driven framework for expressive performance. In this framework, expressive parameters are modeled as a function of score features, i.e., numerical encodings of specific aspects of a musical score, using neural networks. With the proposed interface, users are able to weight the contribution of individual score features and understand how an expressive performance is constructed.

Carlos Cancino-Chacón, Maarten Grachten

Expressive variations of tempo and dynamics are an important aspect of music performances, involving a variety of underlying factors. Previous work has showed a relation between such expressive variations (in particular expressive tempo) and perceptual characteristics derived from the musical score, such as musical expectations, and perceived tension. In this work we use a computational approach to study the role of three measures of tonal tension proposed by Herremans and Chew (2016) in the prediction of expressive performances of classical piano music. These features capture tonal relationships of the music represented in Chew's spiral array model, a three dimensional representation of pitch classes, chords and keys constructed in such a way that spatial proximity represents close tonal relationships. We use non-linear sequential models (recurrent neural networks) to assess the contribution of these features to the prediction of expressive dynamics and expressive tempo using a dataset of Mozart piano sonatas performed by a professional concert pianist. Experiments of models trained with and without tonal tension features show that tonal tension helps predict change of tempo and dynamics more than absolute tempo and dynamics values. Furthermore, the improvement is stronger for dynamics than for tempo.

Carlos Cancino-Chacón, Martin Bonev, Amaury Durand et al.

In this paper we present a preliminary version of the ACCompanion, an expressive accompaniment system for MIDI input. The system uses a probabilistic monophonic score follower to track the position of the soloist in the score, and a linear Gaussian model to compute tempo updates. The expressiveness of the system is powered by the Basis-Mixer, a state-of-the-art computational model of expressive music performance. The system allows for expressive dynamics, timing and articulation.

Maarten Grachten, Carlos Eduardo Cancino Chacón

A remarkable feature of human beings is their capacity for creative behaviour, referring to their ability to react to problems in ways that are novel, surprising, and useful. Transformational creativity is a form of creativity where the creative behaviour is induced by a transformation of the actor's conceptual space, that is, the representational system with which the actor interprets its environment. In this report, we focus on ways of adapting systems of learned representations as they switch from performing one task to performing another. We describe an experimental comparison of multiple strategies for adaptation of learned features, and evaluate how effectively each of these strategies realizes the adaptation, in terms of the amount of training, and in terms of their ability to cope with restricted availability of training data. We show, among other things, that across handwritten digits, natural images, and classical music, adaptive strategies are systematically more effective than a baseline method that starts learning from scratch.

Carlos Cancino-Chacón, Maarten Grachten, David R. W. Sears et al.

In this paper we present preliminary work examining the relationship between the formation of expectations and the realization of musical performances, paying particular attention to expressive tempo and dynamics. To compute features that reflect what a listener is expecting to hear, we employ a computational model of auditory expectation called the Information Dynamics of Music model (IDyOM). We then explore how well these expectancy features -- when combined with score descriptors using the Basis-Function modeling approach -- can predict expressive tempo and dynamics in a dataset of Mozart piano sonata performances. Our results suggest that using expectancy features significantly improves the predictions for tempo.

Carlos Cancino-Chacón, Maarten Grachten, Kat Agres

Tonal structure is in part conveyed by statistical regularities between musical events, and research has shown that computational models reflect tonal structure in music by capturing these regularities in schematic constructs like pitch histograms. Of the few studies that model the acquisition of perceptual learning from musical data, most have employed self-organizing models that learn a topology of static descriptions of musical contexts. Also, the stimuli used to train these models are often symbolic rather than acoustically faithful representations of musical material. In this work we investigate whether sequential predictive models of musical memory (specifically, recurrent neural networks), trained on audio from commercial CD recordings, induce tonal knowledge in a similar manner to listeners (as shown in behavioral studies in music perception). Our experiments indicate that various types of recurrent neural networks produce musical expectations that clearly convey tonal structure. Furthermore, the results imply that although implicit knowledge of tonal structure is a necessary condition for accurate musical expectation, the most accurate predictive models also use other cues beyond the tonal structure of the musical context.

Thassilo Gadermaier, Maarten Grachten, Carlos Eduardo Cancino Chacón

This paper describes a computational model of loudness variations in expressive ensemble performance. The model predicts and explains the continuous variation of loudness as a function of information extracted automatically from the written score. Although such models have been proposed for expressive performance in solo instruments, this is (to the best of our knowledge) the first attempt to define a model for expressive performance in ensembles. To that end, we extend an existing model that was designed to model expressive piano performances, and describe the additional steps necessary for the model to deal with scores of arbitrary instrumentation, including orchestral scores. We test both linear and non-linear variants of the extended model n a data set of audio recordings of symphonic music, in a leave-one-out setting. The experiments reveal that the most successful model variant is a recurrent, non-linear model. Even if the accuracy of the predicted loudness varies from one recording to another, in several cases the model explains well over 50% of the variance in loudness.

Maarten Grachten, Carlos Eduardo Cancino-Chacón, Thassilo Gadermaier et al.

Many people enjoy classical symphonic music. Its diverse instrumentation makes for a rich listening experience. This diversity adds to the conductor's expressive freedom to shape the sound according to their imagination. As a result, the same piece may sound quite differently from one conductor to another. Differences in interpretation may be noticeable subjectively to listeners, but they are sometimes hard to pinpoint, presumably because of the acoustic complexity of the sound. We describe a computational model that interprets dynamics---expressive loudness variations in performances---in terms of the musical score, highlighting differences between performances of the same piece. We demonstrate experimentally that the model has predictive power, and give examples of conductor ideosyncrasies found by using the model as an explanatory tool. Although the present model is still in active development, it may pave the road for a consumer-oriented companion to interactive classical music understanding.