This paper introduces DeepBach, a graphical model aimed at modeling polyphonic music and specifically hymn-like pieces. We claim that, after being trained on the chorale harmonizations by Johann Sebastian Bach, our model is capable of generating highly convincing chorales in the style of Bach. DeepBach’s strength comes from the use of pseudo-Gibbs sampling coupled with an adapted representation of musical data. This is in contrast with many automatic music composition approaches which tend to compose music sequentially. Our model is also steerable in the sense that a user can constrain the generation by imposing positional constraints such as notes, rhythms or cadences in the generated score. We also provide a plugin on top of the MuseScore music editor making the interaction with DeepBach easy to use.

Most works in automatic music generation have addressed so far specific tasks. Such a reductionist approach has been extremely successful and some of these tasks have been solved once and for all. However, few works have addressed the issue of generating automatically fully fledged music material, of human-level quality. In this article, we report on a specific experiment in holistic music generation: the reorchestration of Beethoven’s Ode to Joy , the European anthem, in seven styles. These reorchestrations were produced with algorithms developed in the Flow Machines project and within a short time frame. We stress the benefits of having had such a challenging and unifying goal, and the interesting problems and challenges it raised along the way.

Markov processes are widely used to generate sequences that imitate a given style, using random walk. Random walk generates sequences by iteratively concatenating states to prefixes of length equal or less than the given Markov order}. However, at higher orders, Markov chains tend to replicate chunks of the corpus with a size possibly higher than the order, a primary form of plagiarism. The Markov order defines a maximum length for training but not for generation. In the framework of constraint satisfaction (CSP), we introduce MaxOrder. This global constraint ensures that generated sequences do not include chunks larger than a given maximum order. We exhibit an automaton that recognises the solution set, with a size linear in the size of the corpus. We propose a linear-time procedure to generate this automaton from a corpus and a given max order. We then use this automaton to achieve generalised arc consistency for the MaxOrder constraint, holding on a sequence of size n, in O(n.T) time, where T is the size of the automaton. We illustrate our approach by generating text sequences from text corpora with a maximum order guarantee, effectively controlling plagiarism.

We introduce the problem of generating musical leadsheets, i.e. a melody with chord labels, in the style of an arbitrary composer, that satisfy arbitrary user constraints. The problem is justified by the very nature of musical creativity, as many composers create music precisely by imitating a given style to which they add their own constraints. We propose a solution of this problem by formulating it as a Markov constraint problem. Markov constraints enable users to create stylistically imitative leadsheets that satisfy a large palette of constraints. We show that generated leadsheets are stylistically consistent by reclassifying them using Markov classifiers.

Markov processes are increasingly used to generate finite-length sequences that imitate a given style. However, Markov processes are notoriously difficult to control. Recently, Markov constraints have been introduced to give users some control on generated sequences. Markov constraints reformulate finite-length Markov sequence generation in the framework of constraint satisfaction (CSP). However, in practice, this approach is limited to local constraints and its performance is low for global constraints, such as cardinality or arithmetic constraints. This limitation prevents generated sequences to follow structural properties which are independent of the style, but inherent to the domain, such as meter. In this article, we introduce meter, a constraint that ensures a sequence is 1) Markovian with regards to a given corpus and 2) follows metrical rules expressed as cumulative cost functions. Additionally, meter can simultaneously enforce cardinality constraints. We propose a domain consistency algorithm whose complexity is pseudo-polynomial. This result is obtained thanks to a theorem on the growth of sumsets by Khovanskii. We illustrate our constraint on meter-constrained music generation problems that were so far not solvable by any other technique.

Loop pedals are real-time samplers that playback audio played previously by a musician. Such pedals are routinely used for music practice or outdoor "busking". However, loop pedals always playback the same material, which can make performances monotonous and boring both to the musician and the audience, preventing their widespread uptake in professional concerts. In response, we propose a new approach to loop pedals that addresses this issue, which is based on an analytical multi-modal representation of the audio input. Instead of simply playing back prerecorded audio, our system enables real-time generation of an audio accompaniment reacting to what is currently being performed by the musician. By combining different modes of performance - e.g. bass line, chords, solo - from the musician and system automatically, solo musicians can perform duets or trios with themselves, without engendering the so-called canned (boringly repetitive and unresponsive) music effect of loop pedals. We describe the technology, based on supervised classification and concatenative synthesis, and then illustrate our approach on solo performances of jazz standards by guitar. We claim this approach opens up new avenues for concert performance.

Many systems use Markov models to generate finite-length sequences that imitate a given style. These systems often need to enforce specific control constraints on the sequences to generate. Unfortunately, control constraints are not compatible with Markov models, as they induce long-range dependencies that violate the Markov hypothesis of limited memory. Attempts to solve this issue using heuristic search do not give any guarantee on the nature and probability of the sequences generated. We propose a novel and efficient approach to controlled Markov generation for a specific class of control constraints that 1) guarantees that generated sequences satisfy control constraints and 2) follow the statistical distribution of the initial Markov model. Revisiting Markov generation in the framework of constraint satisfaction, we show how constraints can be compiled into a nonhomogeneous Markov model, using arc-consistency techniques and renormalization. We illustrate the approach on a melody generation problem and sketch some realtime applications in which control constraints are given by gesture controllers.

This paper addresses the problem of automatically extracting perceptive information from acoustic signals, in a supervised classification context. Global labels, i.e., atomic information describing a music title in its entirety, such as its genre, mood, main instruments, or type of vocals, are entered by humans. Classifiers are trained to map audio features to these labels. However, the performances of these classifiers on individual labels are rarely satisfactory. In the case we have to predict several labels simultaneously, we introduce a correction scheme to improve these performances. In this scheme-an instance of the classifier fusion paradigm-an extra layer of classifiers is built to exploit redundancies between labels and correct some of the errors coming from the individual acoustic classifiers. We describe a series of experiments aiming at validating this approach on a large-scale database of music and metadata (about 30 000 titles and 600 labels per title). The experiments show that the approach brings statistically significant improvements.

Electronic Music Distribution is in need of robust and automatically extracted music descriptors. An important attribute of a piece of polyphonic music is what is commonly referred to as "the way it sounds". While there has been a large quantity of research done to model the timbre of individual instruments, little work has been done to analyze "real world" timbre mixtures such as the ones found in popular music. In this paper, we present our research about such "polyphonic timbres". We describe an effective way to model the textures found in a given music signal, and show that such timbre models provide new solutions to many issues traditionally encountered in music signal processing and music information retrieval. Notably, we describe their applications for music similarity, segmentation and pattern induction.

Abstract The intentionally ambiguous expression “Popular Music Browser” reflects the two main goals of this project, which started in 1998, at Sony Computer Science Laboratories. First, we are interested in human‐centered issues related to browsing “Popular Music.” Popular here means that the music accessed is distributed widely and known to many listeners. Second, we consider “popular browsing” of music, i.e., making music accessible to nonspecialists (music lovers) and allowing sharing of musical tastes and information within communities, departing from the usual, single‐user view of digital libraries. This research project covers all areas of the music‐to‐listener chain, from music description, descriptor extraction from the music signal, or data mining techniques, similarity‐based access, and novel music retrieval methods such as automatic sequence generation, and to user interface issues. This article describes the scientific and technical issues at stake and the results obtained, and is illustrated by prototypes developed within the European IST projectCuidado.

The issue of generating automatically sequences of music titles that satisfy arbitrary criteria such as user preferences has gained interest recently, because of the numerous applications in the field of electronic music distribution. All the approaches proposed so far suffer from two main drawbacks: reduced expressiveness and incapacity to handle large music catalogues. We present in this paper a system that is able to produce automatically music playlists out of large, real catalogues (up to 200000 titles), and that can handle arbitrarily complex criteria. We describe the basic algorithm and its adaptation to playlist generation, and report on experiments performed in the context of the European project Cuidado.

We develop mdtimedia technology for enriching the music fitening eqerience.We propose a system-MdiSpace -in which mers may kten to music \vMe controtig in rd tie the lo-ation of sound sourcw, through a simple interface.We introduce the problem of mtiiizg co~zsfite~zcy, and propose a solution based on a constraint propagation mechbm.The proposed system contains both m authoring mode, in which sound engineers may specify spati*ation constraints to be satisfied, and a fitening mode in which kteners m modify the Io&tion of sources under the Supetilon of a constraint solver that ensures the spati~ation always satisfies the constraints.We describe the architecture of the system =d report on e~eriments done so far. Ke~ords3-D sound, spatitiition, constraints, interactive music. AC-LIS~~GT?re befieve that fistening environments of the future can be greatiy enhanced by inte=mting models of musical perception into musicrd 5stening devices, provided we develop appropriate software technolo=~to exploit them ~s is the basis of the research conductti on "Active Estening" at Sony Computer Science bboratory, Paris.Permissionto make dIgilal or hard copies of afl or part of this work for pemonal or classroom use is granted wlxhout fee provided that copies are not made or distributed for profit or commercial advantage, and that copies bear this noti~and the full citation on the first page.To copy othem~e.10republish to post on servers or to redistribute to lists, requires prior specific perrrtrsslonand'ora fee.ACk4hlullimedia'9S.Bristol.UK .0 199SAChl 1-5S11>036-S[9S,'000S S5.00