A musical system for emotional expression

The automatic control of emotional expression in music is a challenge that is far from being solved. This paper describes research conducted with the aim of developing a system with such capabilities. The system works with standard MIDI files and develops in two stages: the first offline, the second online. In the first stage, MIDI files are partitioned in segments with uniform emotional content. These are subjected to a process of features extraction, then classified according to emotional values of valence and arousal and stored in a music base. In the second stage, segments are selected and transformed according to the desired emotion and then arranged in song-like structures.The system is using a knowledge base, grounded on empirical results of works of Music Psychology that was refined with data obtained with questionnaires; we also plan to use data obtained with other methods of emotional recognition in a near future. For the experimental setups, we prepared web-based questionnaires with musical segments of different emotional content. Each subject classified each segment after listening to it, with values for valence and arousal. The modularity, adaptability and flexibility of our system’s architecture make it applicable in various contexts like video-games, theater, films and healthcare contexts.     

Wavelet ridges for musical instrument classification

The time-varying frequency structure of musical signals have been analyzed using wavelets by either extracting the instantaneous frequency of signals or building features from the energies of sub-band coefficients. We propose to benefit from a combination of these two approaches and use the time-frequency domain energy localization curves, called as wavelet ridges, in order to build features for classification of musical instrument sounds. We evaluated the representative capability of our feature in different musical instrument classification problems using support vector machine classifiers. The comparison with the features based on parameterizing the wavelet sub-band energies confirmed the effectiveness of the proposed feature.     

Using machine-learning methods for musical style modeling

The ability to construct a musical theory from examples presents a great intellectual challenge that, if successfully met, could foster a range of new creative applications. Inspired by this challenge, we sought to apply machine-learning methods to the problem of musical style modeling. Our work so far has produced examples of musical generation and applications to a computer-aided composition system. Machine learning consists of deriving a mathematical model, such as a set of stochastic rules, from a set of musical examples. The act of musical composition involves a highly structured mental process. Although it is complex and difficult to formalize, it is clearly far from being a random activity. Our research seeks to capture some of the regularity apparent in the composition process by using statistical and information theoretic tools to analyze musical pieces. The resulting models can be used for inference and prediction and, to a certain extent, to generate new works that imitate the style of the great masters.     

Toward an expert system for expressive musical performance

The development and implementation of an expert system that determines the tempo and articulations of Bach fugues are described. The rules in the knowledge base are based on the expertise of two professional performers. The system's input is a numeric representation of the fugue. The system processes the input using a transition graph, a data structure consisting of nodes where data is stored and edges that connect the nodes. The transition graph recognizes rhythmic patterns in the input. Once the system identifies a pattern, it applies a specific rule or performs a procedure. System output consists of a listing of tempo and articulation instructions. To validate the expert system, its output was compared with versions of fugues edited by one of the two experts used in developing the system. In tests with six fugues, the expert system generated the same editing instructions 85 to 90% of the time     

Global robust output regulation for output feedback systems

The global robust output regulation problem for the class of nonlinear systems in output feedback form has been studied under the assumption that the solution of the regulator equations is polynomial. This assumption essentially requires these systems contain only polynomial nonlinearity and is due to the failure of finding a nonlinear internal model to account for more complex nonlinearities than polynomials. Recently, it was found that a nonlinear internal model can be constructed under some assumption much milder than the polynomial assumption. In this note, we will apply this type of internal model to solve the global robust output regulation problem for the class of nonlinear systems in output feedback form.     

Comparison of musical sequences

Concepts from the theory of sequence comparison are adapted to measure the overall similarity or dissimilarity between two musical scores. A key element is the notion of consolidation and fragmentation, different both from the deletions and insertions familiar in sequence comparison, and from the compressions and expansions of time warping in automatic speech recognition. The measure of comparison is defined so as to detect similarities in melodic line despite gross differences in key, mode or tempo. A dynamic programming algorithm is presented for calculating the measure, and is programmed and applied to a set of variations on a theme by Mozart. Cluster analysis and spatial representation of the results confirm subjective impressions of the patterns of similarities among the variations. A generalization of the algorithm is presented for detecting locally similar portions in two scores, and is then applied.Marcel Mongeau obtained his B.Sc. and M.Sc. degrees at the Université de Montréal and is currently completing his doctorate at the University of Waterloo.David Sankoff (Ph.D., McGill) is a Professor in the Département de mathématiques et statistique and is also attached to the Centre de recherches mathématiques at the Université de Montréal. His research intersts include sociolinguistics — specifically the quantitative approach inherent in linguistic variation theory — statistical classification theory, biomathematics and computational biology — particularly algorithms for macromolecular sequence analysis and the reconstruction of phylogenetic trees.     

Synchronization of musical words

We study the synchronization of musical sequences by means of an operation defined on finite or infinite words called superimposition. This operation can formalize basic musical structures such as melodic canons and serial counterpoint. In the case of circular canons, we introduce the superimposition of infinite words, and we present an enumeration algorithm involving Lyndon words, which appear to be a useful tool for enumerating periodic musical structures. We also define the superimposition of finite words, the superimposition of languages, and the iterated superimposition of a language, which is applied to the study of basic aspects of serial music. This leads to the study of closure properties of rational languages of finite words under superimposition and iterated superimposition. The rationality of the transduction associated with the superimposition appears to be a powerful argument in the proof of these properties. Since the superimposition of finite words is the max operation of a sup-semilattice, the last section addresses the link between the rationality of a sup-semilattice operation and the rationality of the order relation associated with it.     

Algorithms for musical composition: a question of granularity

Early approaches to computer-generated music are examined, and it is argued that making music is concerned with a higher level of granularity than that of the notes on music paper. Work in artificial intelligence shows that low-level decisions such as the selection of individual notes may actually be subordinate to a model-based control structure, the models being examples of how problems have been resolved. It is suggested that the search for algorithmic rules should be directed by two questions: how to identify units of material of the appropriate granularity, and, given a collection of those units, how to properly assemble them     

Formalizing planning knowledge for hierarchical planning

A hierarchical planning system achieves efficiency by planning with the most important conditions first, and considering details later in the planning process. Few attempts have been made to formalize the structure of the planning knowledge for hierarchical planning. For a given domain, there is usually more than one way to define its planning knowledge. Some of the definitions can lead to efficient planning, while others may not. In this paper, we provide a set of restrictions which defines the relationships between a non-primitive action and its set of subactions. When satisfied, these restrictions guarantee improved efficiency for hierarchical planning. One important feature of these restrictions is that they are syntactic and therefore do not depend on the particular structure of any plan. Along with these restrictions, we also provide algorithms for preprocessing the planning knowledge of a hierarchical planner. When used during planning, the preprocessed operator hierarchies can enable a planner to significantly reduce its search space.     

Stabilization via dynamic output feedback for systems with output nonlinearities

The problem of asmptotically stabilizing a class of systems by means of continuous output feedback is considered. These systems are characterized by nonlinear terms, depending only on the ouputs. It is shown that for these systems stabilization via continuous state-feedback plus stabilization via output injection imply stabilization via continuous dynamic output-feedback. This generalizes a well-knwon result for linear systems.     

A study on feature analysis for musical instrument classification.

In tackling data mining and pattern recognition tasks, finding a compact but effective set of features has often been found to be a crucial step in the overall problem-solving process. In this paper, we present an empirical study on feature analysis for recognition of classical instrument, using machine learning techniques to select and evaluate features extracted from a number of different feature schemes. It is revealed that there is significant redundancy between and within feature schemes commonly used in practice. Our results suggest that further feature analysis research is necessary in order to optimize feature selection and achieve better results for the instrument recognition problem.     

NetNeg: A connectionist-agent integrated system for representing musical knowledge

The system presented here shows the feasibility of modeling the knowledge involved in a complex musical activity by integrating sub-symbolic and symbolic processes. This research focuses on the question of whether there is any advantage in integrating a neural network together with a distributed artificial intelligence approach within the music domain. The primary purpose of our work is to design a model that describes the different aspects a user might be interested in considering when involved in a musical activity. The approach we suggest in this work enables the musician to encode his knowledge, intuitions, and aesthetic taste into different modules. The system captures these aspects by computing and applying three distinct functions: rules, fuzzy concepts, and learning. As a case study, we began experimenting with first species two-part counterpoint melodies. We have developed a hybrid system composed of a connectionist module and an agent-based module to combine the sub-symbolic and symbolic levels to achieve this task. The technique presented here to represent musical knowledge constitutes a new approach for composing polyphonic music. This revised version was published online in June 2006 with corrections to the Cover Date.     

Protein output for DNA computing

In recent years, several strategies for DNA based molecular computing have been investigated. An important area of research is the detection and analysis of output molecules. We demonstrate how DNA computing can be extended with in vivo translation of the output. In the resulting proteins, the information per kilogram is about 15-fold higher than in the original DNA output. The proteins are therefore of correspondingly smaller mass, which facilitates their subsequent detection using highly sensitive mass spectrometry methods. We have tested this approach on an instance of the Minimal Dominating Set problem. The DNA used in the computation was constructed as an open reading frame in a plasmid, under the control of a strong inducible promoter. Sequential application of restriction endonucleases yielded a library of potential solutions to the problem instance. The mixture of plasmids was then used for expression of a protein representation. Using MALDI-TOF mass spectrometry, a protein corresponding to the correct solution could be detected. The results indicate the feasibility of the extension of DNA computing to include protein technology. Our strategy opens up new possibilities for both scaling of DNA computations and implementations that employ output of functional molecules or phenotypes.     

Periodic musical sequences and Lyndon words

When one enumerates periodic musical structures, the computation is done up to a cyclic shift. This means that two solutions which are cyclic shifts of one another are considered the same. Lyndon words provide a powerful way to do so. We illustrate this by two examples taken from African traditional music.     

Conditions for exponomial output control

A closed-form expression for the output of a multivariable linear system with an input that is the product of a polynomial vector and an exponential function is derived without reference to the theory of the Laplace transform. When the exponent of the exponential factor in the input coincides with one of the natural modes (eigenvalues) of the system, the Drazin inverse of a matrix is used to derive a closed-form expression for the output. Using this expression, necessary and sufficient conditions for an input to produce a predetermined output are derived. These conditions are expressed in terms of a block matrix known as the system matrix. These results include some results appearing in the literature dealing with the problem of characterizing those input functions that will yield zero output. A tracking result is included which shows that, for a stable system, asymptotic tracking of a predetermined reference signal is possible if, and only if, the signal can be tracked instantaneously.     

Precise pitch profile feature extraction from musical audio for key detection

The majority of pieces of music, including classical and popular music,are composed using music scales, such as keys. The key or the scale information of a piece provides important clues on its high level musical content, like harmonic and melodic context. Automatic key detection from music data can be useful for music classification, retrieval or further content analysis. Many researchers have addressed key finding from symbolically encoded music(MIDI); however, works for key detection in musical audio is still limited. Techniques for key detection from musical audio mainly consist of two steps:pitch extraction and key detection. The pitch feature typically characterizes the weights of presence of particular pitch classes in the music audio. In the existing approaches to pitch extraction, little consideration has been taken on pitch mistuning and interference of noisy percussion sounds in the audio signals, which inevitably affects the accuracy of key detection. In this paper, we present a novel technique of precise pitch profile feature extraction, which deals with pitch mistuning and noisy percussive sounds. The extracted pitch profile feature can characterize the pitch content in the signal more accurately than the previous techniques, thus lead to a higher key detection accuracy. Experiments based on classical and popular music data were conducted. The results showed that the proposed method has higher key detection accuracy than previous methods, especially for popular music with a lot of noisy drum sounds.