Corpus ID: 2403035

Computer-Aided Orchestration Based on Probabilistic Instruments Models and Genetic Exploration

  title={Computer-Aided Orchestration Based on Probabilistic Instruments Models and Genetic Exploration},
  author={Damien Tardieu and Gr{\'e}goire Carpentier and Xavier Rodet},
In this paper we introduce a tool aimed at assisting composers in orchestration tasks. Thanks to this tool, composers can specify a target sound and replicate it with a given orchestra. We discuss the problems raised by the realization of such a tool, concerning instrumental sound description and combinatorial optimization. Then we describe the solution adopted. We propose a machine learning method based on generative probabilistic modeling to represent and generalize instrument timbre… Expand
On Computer-Assisted Orchestration
Almost 10 years after the start of this research project, it is time to look back at what was accomplished from the musical stand point, and to open some new perspectives on the subject, like the introduction of target descriptors for orchestral qualities, and Orchestral layers. Expand
i-Berlioz: Towards Interactive Computer-Aided Orchestration with Temporal Control
i-Berlioz is introduced, a proof-of-concept interactive Computer-Aided Orchestration (CAO) system that suggests combinations of musical instruments to produce timbres specified by the user by means of verbal descriptors, and its generative and exploratory engines. Expand
Towards Intelligent Orchestration Systems
Orchestration is a problem that has been relatively unexplored in computer music until recently. This is perhaps due to its complexity. This paper presents a survey of the field of computer-assistedExpand
i-Berlioz: Interactive Computer-Aided Orchestration with Temporal Control
This paper introduces the beta version of i-Berlioz, an interactive CAO system that generates orchestrations from verbal timbre descriptors. This system relies on machine learning models for timbreExpand
Enhancing Orchestration Technique via Spectrally Based Linear Algebra Methods
The proposed tool (Linear Algebra Based ORCHestration) uses a bank of Discrete Fourier Transforms of orchestral sounds, which are accessed in different ways designed to either perform sound analysis or propose orchestrations that imitate the energetic pattern of a reference sound. Expand
An Investigation into the Use of Artificial Intelligence Techniques for the Analysis and Control of Instrumental Timbre and Timbral Combinations
This research demonstrates that perceptual characteristics of timbral qualities, using verbal descriptors as a representation, can be implemented in an intelligent computing system designed to combine sampled instrument notes conveying specific perceptual qualities. Expand
Science and Technology of Music and Sound: The IRCAM Roadmap
The roadmap for the research and development activities at IRCAM for the period from 2007 to 2010 is presented, through noticeably the introduction of the unifying notion of representation levels of musical information. Expand
A pattern oriented data structure for interactive computer music
This essay describes a pattern oriented data structure, or PODS, as a system for storing computer music data. It organizes input by sequences or patterns that recur, while extensively interlinkingExpand
Multiobjective time series matching and classification
Plusieurs millions d’annees d’evolution genetique ont faconne notre systeme auditif, permettant d’effectuer une discrimination flexible des evenements acoustiques. Nous pouvons ainsi traiterExpand


An Evolutionary Approach to Computer-Aided Orchestration
The orchestration problem can be viewed as a multi-objective 0/1 knapsack problem, with additional constraints and a case-specific criteria formulation, and an hybrid evolutionary algorithm for computer-aided orchestration is introduced. Expand
SPORCH: An Algorithm for Orchestration Based on Spectral Analyses of Recorded Sounds
SPORCH (SPectral ORCHestrater) is a Lisp based computer program that provides orchestrations for any ensemble of acoustic instruments based on any arbitrary sound file input. The result, when played,Expand
Simulation of Human voice Timbre by Orchestration of acoustic Music Instruments
A method which simulates the timbre of the human voice through the orchestration of classic music instrumental ensembles through the spectral envelope of speech, which was applied in the orchestra piece Nicanor, premiered 1999 in Stuttgart. Expand
Product of Gaussians for speech recognition
This paper presents a particular implementation of PoEs, the normalised product of Gaussians (PoG), which allows the classification of variable length data, such as speech data, within a hidden Markov model framework. Expand
Spectral voice conversion for text-to-speech synthesis
  • A. Kain, Michael W. Macon
  • Computer Science
  • Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181)
  • 1998
A new voice conversion algorithm that modifies a source speaker's speech to sound as if produced by a target speaker is presented and is found to perform more reliably for small training sets than a previous approach. Expand
Combining Probability Distributions: A Critique and an Annotated Bibliography
A taxonomy of solutions is presented which serves as the framework for a survey of recent theoretical developments in the area and a number of current research directions are mentioned and an extensive, current annotated bibliography is included. Expand
Fundamental frequency estimation and tracking using maximum likelihood harmonic matching and HMMs
  • B. Doval, X. Rodet
  • Mathematics, Computer Science
  • 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing
  • 1993
A new approach is presented for the estimation and tracking of the fundamental frequency of pseudoperiodic signals based on a probabilistic model that makes it possible to take prior knowledge into account and to include constraints on the evolution of the signal. Expand
Perceptual scaling of synthesized musical timbres: Common dimensions, specificities, and latent subject classes
The model with latent classes and specificities gave a better fit to the data and made the acoustic correlates of the common dimensions more interpretable, suggesting that musical timbres possess specific attributes not accounted for by these shared perceptual dimensions. Expand
The role of similarity in categorization: providing a groundwork
A reassessment of evidence indicates that similarity can be sufficiently constrained and sophisticated to provide at least a partial account of many categories. Expand
Knapsack Problems: Algorithms and Computer Implementations
This paper focuses on the part of the knapsack problem where the problem of bin packing is concerned and investigates the role of computer codes in the solution of this problem. Expand