Learning to Create Jazz Melodies Using Deep Belief Nets
نویسندگان
چکیده
We describe an unsupervised learning technique to facilitate automated creation of jazz melodic improvisation over chord sequences. Specifically we demonstrate training an artificial improvisation algorithm based on unsupervised learning using deep belief nets, a form of probabilistic neural network based on restricted Boltzmann machines. We present a musical encoding scheme and specifics of a learning and creational method. Our approach creates novel jazz licks, albeit not yet in real-time. The present work should be regarded as a feasibility study to determine whether such networks could be used at all. We do not claim superiority of this approach for pragmatically creating jazz.
منابع مشابه
Learning to Create Jazz Melodies Using a Product of Experts
We describe a neural network architecture designed to learn the musical structure of jazz melodies over chord progressions, then to create new melodies over arbitrary chord progressions from the resulting connectome (representation of neural network structure). Our architecture consists of two sub-networks, the interval expert and the chord expert, each being LSTM (long short-term memory) recur...
متن کاملModeling Expressive Music Performance in Jazz
In this paper we describe a machine learning approach to one of the most challenging aspects of computer music: modeling the knowledge applied by a musician when performing a score in order to produce an expressive performance of a piece. We apply machine learning techniques to a set of monophonic recordings of Jazz standards in order to induce both rules and a numeric model for expressive perf...
متن کاملExtensive Deep Belief Nets with Restricted Boltzmann Machine Using MapReduce Framework
Big data is a collection of data sets which is used to describe the exponential growth and availability of both ordered and amorphous data. It is difficult to process big data using traditional data processing applications. In many practical problems, deep learning is one of the machine learning algorithms that has received great popularity in both academia and industry due to its high-level ab...
متن کاملSpherical Signature Description of 3D Point Cloud and Environmental Feature Learning based on Deep Belief Nets for Urban Structure Classification
This paper suggests the method of the spherical signature description of 3D point clouds taken from the laser range scanner on the ground vehicle. Based on the spherical signature description of each point, the extractor of significant environmental features is learned by the Deep Belief Nets for the urban structure classification. Arbitrary point among the 3D point cloud can represents its sig...
متن کاملJazz Melody Generation from Recurrent Network Learning of Several Human Melodies
Recurrent (neural) networks have been deployed as models for learning musical processes, by computational scientists who study processes such as dynamic systems. Over time, more intricate music has been learned as the state of the art in recurrent networks improves. One particular recurrent network, the Long Short-Term Memory (LSTM) network shows promise as a module that can learn long songs, a...
متن کامل