Search

The problem of target-based computer-aided orchestration is a recurring topic in the contemporary music community. Because of its complexity, computer-aided orchestration remains a partially unsolved problem and several systems have been developed in the last twenty years. This article presents a practical overview of the recently introduced Orchidea framework for dynamic computer-aided target-based orchestration. Orchidea continues the line of tools dedicated to the subject (the so-called Orchid* family) originally developed at the Institut de Recherche et Coordination Acoustique/Musique in Paris. Unlike its predecessors, Orchidea uses a combination of optimization techniques that include stochastic matching pursuit, long short-term memory neural networks, and monoobjective evolutionary optimization, with a specifically designed cost function. Symbolic constraints can be integrated in the cost function, and temporally evolving sounds are handled by segmenting them into a set of static targets optimized jointly and then connected. Orchidea is deployed in three different ways: a standalone application, designed to streamline a simplified compositional workflow; a Max package, targeted at composers willing to connect target-based orchestration to the more general area of computer-aided composition; and a set of command-line tools, mostly intended for research purposes and batch processing. The main aim of this article is to present an overview of such software systems and show several instances of the Orchidea framework's application in recent musical productions, tracing the path for future research on the subject.

This article introduces the Orchidea Orchestral Qualities framework (OOQ), an extension of the Orchidea environment for computer-aided orchestration. Traditional target-based orchestration generally reconstructs a target sound “as faithfully as possible” with a collection of samples. But more often than not, composers do not have specific targets in mind while performing orchestration tasks. A large class of orchestration practices deal with the transformation of musical material to enhance or reduce certain of its qualities (such as making a score more “brilliant,” “blurry,” “dense,” and so on). The OOQ framework implements this idea by making use of an analogy with digital signal processing. Scores and sounds are no longer used as targets, but rather as “sources” to be processed, not unlike what happens within a channel strip of a modern digital audio workstation. This article presents the rationale behind the OOQ framework, describes the behavior of its modules, and traces a path for future research on the subject.

We present a new data representation for music modeling and generation called a Flexible Grid. This representation aims to balance flexibility with structure in order to encode all the musical events (notes or rhythmic onsets) in a dataset without quantizing or discarding any temporal information. In experiments with a dataset of MIDI drum performances, we find that when implemented in a Variational AutoEncoder (VAE) model, Flexible Grid representations can enable detailed generation of music performance data that includes multiple different gestures and articulations.

Target-based assisted orchestration can be thought of as the process of searching for optimal combinations of sounds to match a target sound, given a database of samples, a similarity metric, and a set of constraints. A typical solution to this problem is a proposed orchestral score where candidate scores are ranked by similarity in some feature space between the target sound and the mixture of audio samples in the database corresponding to the notes in the score; in the orchestral setting, valid scores may contain dozens of instruments sounding simultaneously. Generally, target-based assisted orchestration systems consist of a combinatorial optimization algorithm and a constraint solver that are jointly optimized to find valid solutions. A key step in the optimization involves generating a large number of combinations of sounds from the database and then comparing the features of each mixture of sounds with the target sound. Because of the high computational cost required to synthesize a new audio file and then compute features for every combination of sounds, in practice, existing systems instead estimate the features of each new mixture using precomputed features of the individual source files making up the combination. Currently, state of the art systems use a simple linear combination to make these predictions, even if the features in use are not themselves linear. In this work, we explore neural models for estimating the features of a mixture of sounds from the features of the component sounds, finding that standard features can be estimated with accuracy significantly better than that of the methods currently used in assisted orchestration systems. We present quantitative comparisons and discuss the implications of our findings for target-based orchestration problems.

[TODO] Add abstract here.

In this article we will propose a new approach for music description, based on the connection between the symbolic (logic) level and the signal level. This approach relies on the possibility of representing sounds in terms of types inferred by some low-level descriptions of signals and subsequent learning stages. We will present simple type theory and we will introduce a twofold process to create aggregate representations with different degrees of abstraction thus making possible to describe and manipulate music at variable conceptual levels.