This contribution gives an overview of the state of the art in the field of computational modeling of expressive music performance. The notion of predictive computational model is briefly discussed, and a number of quantitative models of various aspects of expressive performance are briefly reviewed. Four selected computational models are reviewed in some detail. Their basic principles and assumptions are explained and, wherever possible, empirical evaluations of the models on real performance data are reported. In addition to these models, which focus on general, common principles of performance, currently ongoing research on the formal characterisation of differences in individual performance style are briefly presented. 1.

this paper we present a novel domain for user modeling and intelligent agents -- agents as specific users' improvisational music companions (IMCs). We also introduce Band-OUT-of-a-Box (BoB), an agent designed to trade live, customized solos with a specific improvising musician/user

In many high-level signal processing tasks, such as pitch shifting, voice conversion or sound synthesis, accurate spectral processing is required. Here, the use of Radial Basis Function Networks (RBFN) is proposed for modeling the relationships among sets of spectral envelopes. The identification of such conversion functions is based on a procedure which learns the shape of the conversion from few couples of original target spectra (training set). The generalization properties of RBFNs provides for interpolation with respect to the pitch range. In the construction of the training set, mel-cepstral encoding of the spectrum is used to catch the perceptually most relevant spectral changes. Moreover, singular value decomposition (SVD) is used to reduce the dimension of conversion functions. The RBFN conversion functions introduced are characterized by a perceptually-based fast training procedure, desirable interpolation properties and computational efficiency. 1.

Content processing is a vast and growing field that integrates different approaches borrowed from the signal processing, information retrieval and machine learning disciplines. In this article we deal with a particular type of content processing: the so-called content-based transformations. We will not focus on any particular application but rather try to give an overview of different techniques and conceptual implications. We first describe the transformation process itself, including the main model schemes that are commonly used, which lead to the establishment of the formal basis for a definition of content-based transformations. Then we take a quick look at a general spectral based analysis/synthesis approach to process audio signals and how to extract features that can be used in the content-based transformation context. Using this analysis/synthesis approach we give some examples on how content-based transformations can be applied to modify the basic perceptual axis of a sound and how we can even combine different basic effects in order to perform more meaningful transformations. We finish by going a step further in the abstraction ladder and present transformations that are related to musical (and thus symbolic) properties rather than to those of the sound or the signal itself.

Is there a distinction between New Interfaces for Musical Expression and New Interfaces for Controlling Sound? This article begins with a brief overview of expression in musical performance, and examines some of the characteristics of effective “expressive ” computer music instruments. It becomes apparent that sophisticated musical expression requires not only a good control interface but also virtuosic mastery of the instrument it controls. By studying effective acoustic instruments, choosing intuitive but complex gesture-sound mappings that take advantage of established instrumental skills, designing intelligent characterizations of performance gestures, and promoting long-term dedicated practice on a new interface, computer music instrument designers can enhance the expressive quality of computer music performance.

Creativity is one of the most remarkable characteristics of the human mind. It is thus natural that Artificial Intelligence's research groups have been working towards the study and proposal of adequate computational models to creativity. Artificial creative systems are potentially effective in a wide range of artistic, architectural and engineering domains where detailed problem specification is virtually impossible and, therefore, conventional problem solving is unlikely to produce useful solutions. Moreover their study may contribute to the overall understanding of the mechanisms behind human creativity.

We present here a concatenative sample-based saxophone synthesizer using an induced performance model intended for expressive synthesis. The system consists on three main parts. The first part provides the analysis of saxophone expressive performance recordings and the extraction of descriptors related to different temporal levels. With the obtained descriptors and the analyzed samples, we construct an annotated sample database extracted directly from the performances. For the second part, we use the annotations to induce a performance model capable of predicting some features related to expressivity. In the third part, the predictions of the performance model are used to retrieve the most suitable note samples for each situation, and transform and concatenate them following the input score and the induced model. 1

This chapter gives an introduction into basic strands of current research in expressive music performance. A special focus is given on the various methods to acquire performance data either during a performance (e.g., through computer-monitored instruments) or from audio recordings. We then overview the different computational approaches to formalise and model the various aspects in expressive music performance. Future challenges and open problems are tackled briefly at the end of this chapter. 1.1

One of the main problems with the automatic generation of expressive musical performances is that human performers use musical knowledge that is not explicitly noted in musical scores. Moreover, this knowledge is tacit, difficult to verbalize, and therefore it must be acquired through a process of observation, imitation, and experimentation. For this reason, AI approaches based on declarative knowledge representations have serious limitations. An alternative approach is that of directly using the knowledge implicit in examples from recordings of human performances. In this paper, we describe a case-based reasoning system that generates expressive musical performances based on examples of expressive human performances. 1 Introduction One of the major difficulties in the automatic generation of music is to endow the resulting piece with the expressivity that characterizes human performances. Following musical rules, whatever sophisticated and complete they are, is not enough to a...

This article presents JIG, a system for improvisation on jazz ballads. It was described previously in a Master’s Thesis [4]. JIG generates so called ’formulaic ’ improvisations. It uses constraints, in combination with probability-driven randomness to generate note-attributes. In this way, numerous different improvisations can be generated on a single song. JIG has been incorporated in SaxEx, a case based reasoning system for generating expressive performances of jazz ballads. 1