Learn More
Advances in networking and transmission of digital multimedia data will bring soon huge catalogues of music to users. Accessing these catalogues raises a problem for users and content providers, that we define as the music selection problem. We introduce three main goals to be satisfied in music selection: match user preferences, provide users with new(More)
Advances in networking and transmission of digital multime-dia data bring huge catalogues of multimedia items to users. In the case of music, accessing these catalogues raises a problem for users and content providers, which we define as the music selection problem. From the user point of view, the goals are to match preferences, as well as provide them(More)
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.(More)
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(More)
We propose an extension of Smalltalk with finite-domain constraint satisfaction mechanisms. Our system, called BackTalk, allows the definition of constraints over arbitrary Smalltalk objects, and implements efficient algorithms for constraints satisfaction. We exemplify the use of BackTalk on a problem known to be complex, automatic harmonization. We(More)
We address the issue of generating texts in the style of an existing author, that also satisfy structural constraints imposed by the genre of the text. We focus on song lyrics, for which structural constraints are well-defined: rhyme and meter. Although Markov processes are known to be suitable for representing style, they are difficult to control in order(More)
We describe a large-scale experiment aiming at validating the hypothesis that the popularity of music titles can be predicted from global acoustic or human features. We use a 32.000 title database with 632 manually-entered labels per title including 3 related to the popularity of the title. Our experiment uses two audio feature sets, as well as the set of(More)
Markov processes are widely used to generate sequences that imitate a given style, using random walk. Random walk generates sequences by iteratively con-catenating 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,(More)