Publication

A Distance Model for Rhythms

Samy Bengio, Jean-François Paiement
2008
Conference paper
Abstract

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 distances between subsequences. A specific implementation of the model when considering Hamming distances over a simple rhythm representation is described. The proposed model consistently outperforms a standard Hidden Markov Model in terms of conditional prediction accuracy on two different music databases.

About this result
This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.
Related concepts (33)
Rhythm
Rhythm (from Greek ῥυθμός, rhythmos, "any regular recurring motion, symmetry") generally means a "movement marked by the regulated succession of strong and weak elements, or of opposite or different conditions". This general meaning of regular recurrence or pattern in time can apply to a wide variety of cyclical natural phenomena having a periodicity or frequency of anything from microseconds to several seconds (as with the riff in a rock music song); to several minutes or hours, or, at the most extreme, even over many years.
Polyrhythm
Polyrhythm is the simultaneous use of two or more rhythms that are not readily perceived as deriving from one another, or as simple manifestations of the same meter. The rhythmic layers may be the basis of an entire piece of music (cross-rhythm), or a momentary section. Polyrhythms can be distinguished from irrational rhythms, which can occur within the context of a single part; polyrhythms require at least two rhythms to be played concurrently, one of which is typically an irrational rhythm.
Additive rhythm and divisive rhythm
In music, the terms additive and divisive are used to distinguish two types of both rhythm and meter: A divisive (or, alternately, multiplicative) rhythm is a rhythm in which a larger period of time is divided into smaller rhythmic units or, conversely, some integer unit is regularly multiplied into larger, equal units. This can be contrasted with additive rhythm, in which larger periods of time are constructed by concatenating (joining end to end) a series of units into larger units of unequal length, such as a meter produced by the regular alternation of and .
Show more
Related publications (32)

A Machine Learning-based Framework for Forecasting Sales of New Products With Short Life Cycles Using Deep Neural Networks

Ralf Seifert, Yara Kayyali El Alem

Demand forecasting is becoming increasingly important as firms launch new products with short life cycles more frequently. This paper provides a framework based on state-of-the-art techniques that enables firms to use quantitative methods to forecast sales ...
2022

Learning music composition with recurrent neural networks

Florian François Colombo

Throughout this thesis, we are interested in modeling music composition. To do so, we study the association of music theory concepts with the learning capabilities of recurrent neural networks. Especially, we explore numerical formalizations of music so th ...
EPFL2021

Robust Learning-Augmented Caching: An Experimental Study

Adam Teodor Polak

Effective caching is crucial for performance of modern-day computing systems. A key optimization problem arising in caching – which item to evict to make room for a new item – cannot be optimally solved without knowing the future. There are many classical ...
PMLR2021
Show more

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.