Electronic Music Distribution (EMD) is in demand of robust, automatically extracted music descriptors. We introduce a timbral similarity measures for comparing music titles. This measure is based on a Gaussian model of cepstrum coefficients. We describe the timbre extractor and the corresponding timbral similarity relation. We describe experiments in assessing the quality of the similarity relation, and show that the measure is able to yield interesting similarity relations, in particular when used in conjunction with other similarity relations. We illustrate the use of the descriptor in several EMD applications developed in the context of the Cuidado European project.

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 200,000 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.

In this paper we introduce a system for constructing a constrained sequence of music pieces that satisfy users preferences. The proposed system has the ability to retrieve music excerpts with predefined constraints. These constraints can be related to the nature of the melody, instruments specifications, singer gender, as well as the in between feature differences. The proposed solution to the music selection problem finds applications in online music distribution systems which replace the physical CD which we do not have control on its contents. We adopt a joint network flow model and a vector space interpretation to find the optimal solution. The problem finally is transformed into a linear program which is solvable in a reasonable amount of time. 1.

The CUIDADO Project (Content-based Unified Interfaces and Descriptors for Audio/music Databases available Online) aims at developing a new chain of applications through the use of audio/music content descriptors, in the spirit of the MPEG-7 standard. The project includes the design of appropriate description structures, the development of extractors for deriving high-level information from audio signals, and the design and implementation of two applications: the Sound Palette and the Music Browser. These applications include new features, which systematically exploit high-level descriptors and provide users with content-based access to large catalogues of audio/music material. The Sound Palette focuses on audio samples and targets professional users, whereas the Music Browser addresses a broader user target through the management of Popular music titles. After a presentation of the project objectives and methodology, we describe the original features of the two applications based on the systematic use of descriptors and the technical architecture framework on which they rely.

This paper is concerned with the handling of rhythm in music content processing applications. Keeping this framework in mind, we briefly report on terminology issues and the interdisciplinary nature of rhythm investigations, we then review approaches to computational modeling of rhythm and rhythm representation schemes. We comment the bottomup and top-down oriented approaches to computational modeling and the parallel that some authors make with physiological and cognitive views on rhythm perception. We argue that investigations should be listener-oriented, signal-oriented and application-oriented. 1

Selecting the ‘right ’ songs and putting them in the ‘right’ order are key to a great music listening or dance experience. ‘SatisFly ’ is an interactive playlist generation system in which the user can tell what kind of songs should be contained in what order in the playlist, while she navigates through the music collection. The system uses constraint satisfaction to generate a playlist that meets all user wishes. In a user evaluation, it was found that users created high-quality playlists in a swift way and with little effort using the system, while still having complete control on their music choices. The novel interactive way of creating a playlist, while browsing through the music collection, was highly appreciated. Ease of navigation through a music collection is still an issue that needs further attention.

New media distribution channels have created a strong need for digital media personalization that helps both users and producers get the most of media products. In this paper we concentrate on the customized music delivery issue. We propose an approach for constructing a sequence of tracks that satisfies user requirements and at the same time optimally exploits music catalogs. An optimal solution consists of examining all possible tracks enumeration in the database. This is clearly a combinatorial NP-hard. We use vector space concepts to formulate the constrained sequence retrieval problem as an integer program. Our experiments demonstrates the power of our approximation to the original problem in reducing the search space and producing valid solutions. 1.

this report presents state of the art techniques used to find a specific audio information in an audio database. In addition to bibliographical studies, we have highlighted some drawbacks of current techniques, and investigated some improvements

A system for retrieving a sequence of music excerpts or songs based on users and producers requirements is proposed in this paper. Our system provides a flexible way to retrieve music pieces based on its contents as well as user-defined constraints. The proposed system allows online users to extract a sequence of songs whose first and last tracks are known and at the same time the in-between songs have minimum inter-track differences and satisfy predefined requirements. We model the problem as a constrained minimum cost flow problem which leads to a binary integer linear program (BILP) that can be solved in a reasonable amount of time. 1

Markov chains are a well known tool to model temporal properties of many phenomena, from text structure to fluctuations in economics. Because they are easy to generate, Markovian sequences, i.e. temporal sequences having the Markov property, are also used for content generation applications such as text or music generation that imitate a given style. However, Markov sequences are traditionally generated using greedy, left-to-right algorithms. While this approach is computationally cheap, it is fundamentally unsuited for interactive control. This paper addresses the issue of generating steerable Markovian sequences. We target interactive applications such as games, in which users want to control, through simple input devices, the way the system generates a Markovian sequence, such as a text, a musical sequence or a drawing. To this aim, we propose to revisit Markov sequence generation as a branch and bound constraint satisfaction problem (CSP). We propose a CSP formulation of the basic Markovian hypothesis as elementary Markov Constraints (EMC). We propose algorithms that achieve domain-consistency for the propagators of EMCs, in an event-based implementation of CSP. We show how EMCs can be combined to estimate the global Markovian probability of a whole sequence, and accommodate for different species of Markov generation such as fixed order, variable-order, or smoothing. Such a formulation, although more costly than traditional greedy generation algorithms, yields the immense advantage of being naturally steerable, since control specifications can be represented by arbitrary additional constraints, without any modification of the generation algorithm. We illustrate our approach on simple yet combinatorial chord sequence and melody generation problems and give some performance results.