ISSN:0954-0091    

DOI:10.1080/09540099408915720

出版商:Taylor & Francis Group    

年代:1994

数据来源: Taylor

摘要:

Most modern pitch-perception theories incorporate a pattern-recognition scheme to extract pitch. Typically, this involves matching the signal to be classified against a harmonic-series template for each pitch to find the one with the best fit. Although often successful, such approaches tend to lack generality and may well fail when faced with signals with much depleted or inharmonic components. Here, an alternative method is described, which uses an adaptive resonance theory (ART) artificial neural network (ANN). By training this with a large number of spectrally diverse input signals, we can construct more robust pitch-templates which can be continually updated without having to re-code knowledge already acquired by the ANN. The input signal is Fourier-transformed to produce an amplitude spectrum. A mapping scheme then transforms this to a distribution of amplitude within ‘semitone bins’. This pattern is then presented to an ARTMAP ANN consisting of an ART2 and ART1 unsupervised ANN linked by a map field. The system was trained with pitches ranging over three octaves (C3 to Cf) on a variety of instruments and developed a desirable insensitivity to phase, timbre and loudness when classifying.

ISSN:0954-0091    

DOI:10.1080/09540099408915721

出版商:Taylor & Francis Group    

年代:1994

数据来源: Taylor

摘要:

Modelling how people establish a sense of tonality and encode pitch invariance are important elements of research into musical cognition. This paper describes simulations of processes that induce classifications of pitch and interval use from a set of nursery-rhyme melodies. The classifications are identified with keys and degrees of the scale. The extractive process has been implemented in various forms of shunting, adding and tracking memory, and ART2 networks, Kohonen feature maps and feedforward nets are used as classifiers, in modular combinations. In the model, stable tonal centres emerge as general categories of pitch use over the short to medium term, while degree categories emerge from classifying interval use over the longer term. The representations of degree reflect the similarity relations between degrees. Overall, this research is concerned with the problem of how to abstract representations of sequences in a way that is both resilient and adaptive. It uses various extractive processes cooperatively to derive consistent representations from sequences of pitches, and shows that by using information generated within one process it is possible to guide the development of another, in this case functional representation.

ISSN:0954-0091    

DOI:10.1080/09540099408915722

出版商:Taylor & Francis Group    

年代:1994

数据来源: Taylor

摘要:

Many connectionist approaches to musical expectancy and music composition let the question of ‘What next?’ overshadow the equally important question of ‘When next?’. One cannot escape the latter question, one of temporal structure, when considering the perception of musical meter. We view the perception of metrical structure as a dynamic process where the temporal organization of external musical events synchronizes, or entrains, a listener's internal processing mechanisms. This article introduces a novel connectionist unit, based upon a mathematical model of entrainment, capable of phase- and frequency-locking to periodic components of incoming rhythmic patterns. Networks of these units can self-organize temporally structured responses to rhythmic patterns. The resulting network behavior embodies the perception of metrical structure. The article concludes with a discussion of the implications of our approach for theories of metrical structure and musical expectancy.

ISSN:0954-0091    

DOI:10.1080/09540099408915723

出版商:Taylor & Francis Group    

年代:1994

数据来源: Taylor

摘要:

This is a study of two attempts to develop quantitative models of timing in music performance, one based on connectionism and the other involving the autocorrelation function. The former is concerned with the ‘quantization problem’ of interpreting durations of time from a musical performance as note shapes which represent duration in music notation. The latter is an attempt to represent what makes such performances ‘‘expressive ’. These models were derived by Peter Desain, but there is a paucity of validating data in the published literature. Attempts to collect additional data have revealed significant shortcomings in both models, as well as methodological flaws. The most important problem is that the attempt to solve the quantization problem lacks any representation of high-level structure. As a result, if the music itself tends to be based on relatively irregular rhythmic patterns, the connectionist model can distort even a metronome-perfect performance, rather than recognizing the correct temporal patterns. Attempts are made to explain how these shortcomings may have arisen.

ISSN:0954-0091    

DOI:10.1080/09540099408915724

出版商:Taylor & Francis Group    

年代:1994

数据来源: Taylor

摘要:

A brief review of studies into the psychology of melody perception leads to the conclusion that melodies are represented in long-term memory as sequences of specific items, either intervals or scale notes; the latter representation is preferred. Previous connectionist models of musical-sequence learning are discussed and criticized as models of perception. The Cohen— Grossberg masking field (Cohen & Grossberg, 1987) is described and it is shown how it can be used to generate melodic expectations when incorporated within an adaptive resonance architecture. An improved formulation, the SONNET 1 network (Nigrin, 1990, 1992), is described in detail and modifications are suggested. The network is tested on its ability to learn short melodic phrases taken from a set of simple melodies, before being applied to the learning of the melodies themselves. Mechanisms are suggested for sequence recognition and sequence recall. The advantages of this approach to sequence learning are discussed.

ISSN:0954-0091    

DOI:10.1080/09540099408915725

出版商:Taylor & Francis Group    

年代:1994

数据来源: Taylor

摘要:

In algorithmic music composition, a simple technique involves selecting notes sequentially according to a transition table that specifies the probability of the next note as a function of the previous context. An extension of this transition-table approach is described, using a recurrent autopredictive connectionist network called CONCERT. CONCERT is trained on a set of pieces with the aim of extracting stylistic regularities. CONCERT can then be used to compose new pieces. A central ingredient of CONCERT is the incorporation of psychologically grounded representations of pitch, duration and harmonic structure. CONCERT was tested on sets of examples artificially generated according to simple rules and was shown to learn the underlying structure, even where other approaches failed. In larger experiments, CONCERT was trained on sets of J. S. Bach pieces and traditional European folk melodies and was then allowed to compose novel melodies. Although the compositions are occasionally pleasant, and are preferred over compositions generated by a third-order transition table, the compositions suffer from a lack of global coherence. To overcome this limitation, several methods are explored to permit CONCERT to induce structure at both fine and coarse scales. In experiments with a training set of waltzes, these methods yielded limited success, but the overall results cast doubt on the promise of note-by-note prediction for composition.

ISSN:0954-0091    

DOI:10.1080/09540099408915726

出版商:Taylor & Francis Group    

年代:1994

数据来源: Taylor

摘要:

Music harmonization has long been recognized as a highly intellectual process. Musicologists have studied music pieces by great composers and formulated a number of symbolic rules. However, these rules usually form only a set of heuristics and may not be absolutely precise. In this paper, we demonstrate how to train a Boltzmann machine to capture these syntactic rules and use it to construct an effective Boltzmann machine (EBM) to harmonize some unseen pieces. We have also incorporated ways to apply absolute constraints to the completion process. Our experiments demonstrate that using an EBM, ‘good’ harmonies can be non-deterministically synthesized along with a relative measure of their quality.

ISSN:0954-0091    

DOI:10.1080/09540099408915727

出版商:Taylor & Francis Group    

年代:1994

数据来源: Taylor

摘要:

A method for the evaluation of melody is presented. The method is based on a connectionist operationalation of the aesthetic ideal of unity in diversity. It is demonstrated that one can determine the degree of unity in diversity of a stimulus by measuring the mean activation levels of a competitive network. This measure is then used to show why stepwise motion is favoured in melodies, and why there tends to be a family resemblance between successive melodic groups. Four sets of simulations were then run to further test the model. In the first, it was shown that the model predicts that positive affect is an inverted U-shaped curve as a function of melodic complexity, in accord with human data. The second treats affect and exposure; the model predicts that exposure to a melody will increase affective response to it, but that this quantity will fall off with over-exposure. In the third set of simulations, it is shown that there is positive affective transfer within a musical genre, but relatively little transfer between genres. Finally, it is shown that degraded good melodies induce a decrease in the model's evaluation function. Difficulties with the model are then discussed, and it is suggested that these problems may be addressed by altering the network dynamics but by preserving the affective measure.

ISSN:0954-0091    

DOI:10.1080/09540099408915728

出版商:Taylor & Francis Group    

年代:1994

数据来源: Taylor

摘要:

In 1991, Karl Sims presented work on artificial evolution in which he used genetic algorithms to evolve complex structures for use in computer-generated images and animations. The evolution of the computer-generated images progressed from simple, randomly generated shapes to interesting images which the users created interactively. The evolution advanced under the constant guidance and supervision of the user. This paper describes attempts to automate the process of image evolution through the use of artificial neural networks. The central objective of this study is to learn the user's preferences, and to apply this knowledge to evolve aesthetically pleasing images which are similar to those evolved through interactive sessions with the user. This paper presents a detailed performance analysis of both the successes and shortcomings encountered in the use of five artificial neural network architectures. Further possibilities for improving the performance of a fully automated system are also discussed.

ISSN:0954-0091    

DOI:10.1080/09540099408915729

出版商:Taylor & Francis Group    

年代:1994

数据来源: Taylor