Markov models are extremely useful as a general, widely applicable tool for many areas in
statistical pattern recognition. This unique text/reference places the formalism of Markov …

The dynamic hierarchical Dirichlet process (dHDP) is developed to model complex
sequential data, with a focus on audio signals from music. The music is represented in terms …

Music as a sound symbol can express what people think; music is both a form of social
behavior and can promote people's emotional communication; music is also a form of …

We consider the problem of annotating song changes in DJ-mixed dance music recordings
(pod-casts, radio shows, live events). It is an extremely laborious process to perform this task …

While it has been well established that affect influences judgments and decision-making,
few computational models of the phenomenon exist. The work I have done and propose …

At EPFL, the Montreux Jazz Digital Project aims at digitizing the archives of the Montreux
Jazz Festival (MJF) concerts. A few figures: since 1967, 5000 hours of audio and video are …

Nowadays, many people are expecting an age of personal robots just as what happened in
the evolution of computers. With this background, the research on human-robot interaction …

In this thesis, temporal and spatial dependence are considered within nonparametric priors
to help infer patterns, clusters or segments in data. In traditional nonparametric mixture …

A Bayesian dynamic model is developed to model complex sequential data, with a focus on
audio signals from music. The music is represented in terms of a sequence of discrete …