Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.
AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.
Modeling long-term dependencies in time series has proved very difficult to achieve with traditional machine learning methods. This problem occurs when considering music data. In this paper, we introduce a model for rhythms based on the distributions of di ...
Modeling long-term dependencies in time series has proved very difficult to achieve with traditional machine learning methods. This problem occurs when considering music data. In this paper, we introduce generative models for melodies. We decompose melodic ...
This thesis analyses the city of Buenos Aires as a lived space in its historical context, based on my childhood memories. It characterizes the specific Stimmung that colours the urban and suburban spaces of Buenos Aires in the XIXth and XXth century. I ach ...
Audio segmentation, in general, is the task of segmenting a continuous audio stream in terms of acoustically homogenous regions, where the rule of homogeneity depends on the task. This thesis aims at developing and investigating efficient, robust and unsup ...
Audio segmentation, in general, is the task of segmenting a continuous audio stream in terms of acoustically homogenous regions, where the rule of homogeneity depends on the task. This thesis aims at developing and investigating efficient, robust and unsup ...
This paper reviews the state-of-the-art in automatic genre classification of music collections through three main paradigms: expert systems, unsupervised classification, and supervised classification. The paper discusses the importance of music genres with ...
The motor actions that can be witnessed as a virtuoso musician performs can be so fast, so accomplished, so precise, as to seem somehow superhuman. The musician has to produce the movements, monitor those they have already made and the subsequent result, c ...
Audio segmentation, in general, is the task of segmenting a continuous audio stream in terms of acoustically homogenous regions, where the rule of homogeneity depends on the task. This thesis aims at developing and investigating efficient, robust and unsup ...
In this paper, we present a new approach towards high performance speech/music discrimination on realistic tasks related to the automatic transcription of broadcast news. In the approach presented here, the (local) Probability Density Function (PDF) estima ...