Papers
Sound and Music Computing Conference 2004 (ed. 1)
Dates: from October 20 to October 22, 2004
Place: Paris, France
Proceedings info: not available
2004.1
An Adaptive Multi-parametric and Redundancy-filtering Approach for Motivic Pattern Discovery
Lartillot, Olivier Department of Music, University of Jyväskylä; Jyväskylä, Finland
Abstract
This paper presents the principles of a new approach aimed at automatically discovering motivic patterns in monodies. It is shown that, for the results to agree with the listener’s understanding, computer modelling needs to follow as closely as possible the strategies undertaken during the listening process. Motivic patterns, which may progressively follow different musical dimensions, are discovered through an adaptive incremental identification in a multi-dimensional parametric space. The combinatorial redundancy that would logically result from the model is carefully limited with the help of particular heuristics. In particular, a notion of specificity relation between pattern descriptions is defined, unifying suffix relation – between patterns – and inclusion relation – between the multi-parametric descriptions of patterns. This enables to discard redundant patterns, whose descriptions are less specific than other patterns and whose occurrences are included in the occurrences of the more specific patterns. Periodic repetitions of patterns also induce combinatory proliferations of redundant patterns, which are avoided by modelling patterns as cyclic chains of states. Resulting analyzes come close to the structures actually perceived by the listener.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849147
Zenodo URL: https://zenodo.org/record/849147
2004.2
Applying Aspect Oriented Programming to Music Computing
Hill, Patrick The Open University; Milton Keynes, United Kingdom
Holland, Simon The Open University; Milton Keynes, United Kingdom
Laney, Robin Charles The Open University; Milton Keynes, United Kingdom
Abstract
Computer programs for the composition, performance and analysis of music generally involve the tangled interaction of many dimensions of musical and extramusical concern. In this paper we introduce the concepts of Aspect-Oriented Programming (AOP) to Music Computing and argue that AOP and related techniques and technologies form an appropriate solution to the separation and composition of such concerns. We motivate our argument with simple examples from the musical domain, but argue that the underlying principles may be applied to a wide and expressive range of musical applications.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849149
Zenodo URL: https://zenodo.org/record/849149
2004.3
A Pregroup Grammar for Chord Sequences
Terrat, Richard G. LIRMM, Laboratoire d'Informatique, de Robotique et de Microélectronique de Montpellier (LIRMM); Montpellier, France / Institut de Recherche et Coordination Acoustique/Musique (IRCAM); Paris, France
Abstract
In 1984, Mark STEEDMAN [7] proposed a generative grammar based on six context sensitive rewriting rules able to produce a large variety of blues chord sequences. Later, François PACHET [6] developed a method for analyzing jazz chord sequences. Then, Marc CHEMILLER [4] [5] uses STEEDMAN’s grammar to compose by computers jazz music based upon chord sequences generated by this grammar. About twenty years after his first work, STEEDMAN [8] [9] comes back to chord sequences analysis, but now with the aim of recognition based upon categorial grammars. Meanwhile, pregroup grammars have been conceived as an algebraic tool to recognize well-formed sentences in natural languages [1] [2]. Here we wish to use pregroup grammars to recognize well-formed sequences of chords, especially in Jazz music. Our recognition process reduces the chord sequence to a simpler one. If this later sequence is similar to a well-known pattern like blues, rag, “anatole” or other, we can classify the original sequence as conform to this pattern.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849079
Zenodo URL: https://zenodo.org/record/849079
2004.4
Architecture and Experiments in Networked 3D Audio/Graphic Rendering With Virtual Choreographer
Jacquemin, Christian Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur (LIMSI), Université Paris-Sud XI; Orsay, France
Abstract
The full integration and synchronization of 3D sound and image requires a data model and an architecture that allow for homogeneous description of geometrical and sonic components, together with mechanisms for distributed and synchronized rendering. First, several modes of sound and graphic combination are examined, and the resulting constraints for the rendering tools are detailed. Virtual Choreographer is then described with a particular emphasis on its XML data model for animation of spatialized geometrical and sonic components. An architecture is proposed that relies on the networked connection of Virtual Choreographer and a tool for sound synthesis and event synchronization such as Pure Data or Max/MSP + SPAT for sound spatialization. Last several experiments that involve these tools for different artistic or technical purposes are presented.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849151
Zenodo URL: https://zenodo.org/record/849151
2004.5
A Real-time Beat Tracker for Unrestricted Audio Signals
Scaringella, Nicolas Signal Processing Institute, Ecole Polytechnique Fédérale de Lausanne (EPFL); Lausanne, Switzerland
Zoia, Giorgio Signal Processing Institute, Ecole Polytechnique Fédérale de Lausanne (EPFL); Lausanne, Switzerland
Abstract
Analysis of real music content, not available in symbolic form, still remains a very challenging problem. Promising results can be obtained combining signal processing techniques with intelligent agents, in order to support the often ambiguous results of the analytic phase with smart decision systems, trained by a consistent preliminary knowledge or characterized by forms of learning. In this paper we propose a multiagent algorithm for beat and tempo analysis and induction for unrestricted audio signals; it is based on the combination of lossy onset detection, note accentuation evaluation to estimate metrically essential events, and a multi-agent mechanism to allow dynamic beat tracking. Each agent maintains a self-confidence attribute to rate the confidence for the theory it supports. Consistent test criteria have been used. Experimental results are reported for a database of musical samples from different styles and genres; these results are quite promising. The integration with a harmony analyzer for mutual consolidation is envisaged as next step.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849141
Zenodo URL: https://zenodo.org/record/849141
2004.6
A Role of Metrical Structure in Implicit Memory of Rhythm Perception: Toward a Computational Modeling of Perception Process of Metrical Structure
Goto, Yasuhiro Department of Psychology and Applied Communication, Hokusei Gakuen University; Sapporo, Japan
Abstract
Memory for rhythmic tone sequence plays an important roll in rhythm perce ption and variety of study has been made on it. Previous study suggests, for instance, that more easily it is perceived, more easily it is memorized. In recent years there has been renewal of interest in implicit memory for musical information. In this study, the implicit memory for rhythmic tone sequence was examined. The aim of this study was to investigate the implicit memory for musical rhythm from the viewpoint of cognitive psychology. An experiment using priming and recognition tasks was performed to clarify the nature of implicit memory for rhythmic tone sequences. Two types of measure, binary meter tone sequence and ternary meter tone sequence, were used in experimental variables. In the experiment, encoding strategy was manipulated as an independent measure. In the study phase, half of participants were asked to perform “foot tapping task” and the others were asked to “note counting task.” Foot tapping task means that participants tap their foot to the tone sequence. Note counting task means that participants count the number of the tones. In the test phase, half of the participants performed a priming task: they were asked to judge the familiarity on a 7-point scale (1= not familiar at all, 7= completely familiar). The rest of the participants performed a yes/no recognition test. The pitch height (A4) and timber (piano sound) were the same in both the study phase and the test phase. Priming effect was defined as difference between rating value of familiarity for old tone sequence and new one. The following results were obtained: 1) priming effect was observed in both binary meter and ternary meter tone sequence when listeners were asked to performed “foot tapping task”, 2) priming effect for binary meter tone sequence was bigger than that for ternary meter tone sequence, 3) no significant main effect was observed in the recognition task. These results lead to the conclusion that an implicit memory for musical rhythm exists and the type of metrical structure plays an important role in perceptual priming of rhythmic tone sequences. This may associate with the preference for binary metrical type in rhythm perception.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849143
Zenodo URL: https://zenodo.org/record/849143
2004.7
Classification Into Musical Genres Using a Rhythmic Kernel
Frederico, Gustavo Ottawa University; Ottawa, Canada
Abstract
Beginning with the question on how to determine the genre of a music piece, we elaborate on the representation of rhythm for the classification into genres. The aim of such classification differs in principle from that of traditional Music Informa tion Retrieval algorithms. First, we formalise the rhythmic representation of music fragments. This formalism is then used to construct a similarity function called kernel. To allow the discrete comparison of rhythmic fragments, a pre-processing step in th e algorithm computes a common quantization unit among the input data. A simple injective mapping into RN allows the kernel to employ the Euclidean dot product. A small database of jazz, classical and rock fragments is used in an implementation of a Support Vector Machine. The issues that arise with different time signatures are analysed. Finally, we share some early results of the experiments comparing the three genres, showing that rhythm conveys good information for classification, within the conditions of the experiment.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849155
Zenodo URL: https://zenodo.org/record/849155
2004.8
Composing in the Flesh: Perceptually-informed Harmonic Syntax
Ferguson, Sean Faculty of Music, McGill University; Montreal, Canada
Parncutt, Richard Department of Musicology, University of Graz; Graz, Austria
Abstract
A perceptually-informed harmonic syntax is described in which outer voices are harmonized according to psychoacoustic models of sensory dissonance and successive and referential pitch commonality. These models take into account the spectrums of the notated pitches of a sonority. The harmonic system is implemented using software written by the first author in the Common Lisp programming language. The user defines the relative degrees of each parameter for each member of a given set of outer voices, and the software calculates values for all appropriate chords found within a predetermined harmonic vocabulary. The paper describes one possible method of creating a harmonic vocabulary for a piece. It then provides an overview of the psychoacoustic models that correspond to the harmonic parameters and demonstrates the manner in which progressions are composed. Finally, it gives examples of progressions composed in this way from Dans la chair/In the Flesh, a recent piece for orchestra by the first author.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849157
Zenodo URL: https://zenodo.org/record/849157
2004.9
Composition and Improvisation on the Net
Hajdu, Georg Hochschule für Musik und Theater Hamburg; Hamburg, Germany
Abstract
The interactive network performance environment Quintet.net is a flexible music application, which allows the realization of music and multimedia projects in a local network setting or on the Internet. Special care was taken to accommodate different musical approaches ranging from free improvisation to the performance of compositions with fixed notation. The paper will first give an overview of the notions of improvisation and composition, before describing the environment in some detail. It will conclude with the analysis of select pieces written for Quintet.net.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849159
Zenodo URL: https://zenodo.org/record/849159
2004.10
Control Search Using Rules, Tests and Measures (its Applications in the Harmonisation of Bach's Chorales)
Phon-Amnuaisuk, Somnuk Multimedia University; Cyberjaya, Malaysia
Smaill, Alan Music Informatics Research Group, The University of Edinburgh; Edinburgh, United Kingdom
Abstract
Problem solvings may be viewed as search. In a search, knowledge plays a crucial role in guiding the search to an acceptable solution. We believe that an explicit separation between knowledge levels and the use of knowledge in problem solving allows knowledge-rich systems to be more flexible and powerful. With this aim, appropriate representation framework and inference mechanism are required. This paper discusses the issues involved by viewing effective problem solving through the search control perspective. In this view, the data stream is defined as a stream of problem states returned after applying a control definition to a problem state ( ). The control definition is a control block constructed from three primitives, namely rules, tests and measures. A problem is said to be solved if a sequence of control definitions (control stream) applied to the start state yields the goal state e.g. (). The stream of control procedure utilises knowledge to decide how to move from the start state to the goal state. We explain the search mechanism and how the knowledge can be applied to guide search in this view. We illustrate the approach with a case study in the harmonisation of Bach’s chorales.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849163
Zenodo URL: https://zenodo.org/record/849163
2004.11
Developing a Non-visual Output Device for Musical Performers
Miyashita, Homei Japan Advanced Institute of Science and Technology (JAIST); Nomi, Japan
Nishimoto, Kazushi Japan Advanced Institute of Science and Technology (JAIST); Nomi, Japan
Abstract
Musical performers conduct music information processing while playing, and there are many information flows that they receive visually. The major concern in introducing new systems into live musical performances seems to have been the development of input devices that reflect musical gesture. However, there have been many fewer attempts to develop 'output devices' that convey musical information to the performer. As such an output device, we developed a thermoscore-display that dynamically alters the temperature of the instrument/player interface. We consider that it is well-suited for use as feedback system that denotes the frequency of the occurrence of notes in an improvisation. Also it contributes as special score display, that also conveys a feeling of the existence of the composer.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849165
Zenodo URL: https://zenodo.org/record/849165
2004.12
Etheraction: Playing a Musical Piece Using Graphical Interfaces
Couturier, Jean-Michel Laboratoire de Mécanique et d'Acoustique (LMA); Marseille, France
Abstract
This paper introduces the use of graphical interfaces to interpret an electroacoustic piece, Etheraction. Electroacoustic pieces, commonly created for tape, can now be interpreted in live performance with dedicated interactive systems; the interaction between the performers and these systems can use graphical interfaces, largely implemented in nowadays computers. When using graphical interfaces for real time sound control, the tasks consist in controlling sound parameters through the manipulation of graphical objects, using pointing techniques or direct control with additional devices. The paper presents how I have designed two interactive systems dedicated to interpret in live Etheraction, a multichannel piece I have initially composed for tape. The piece is based on the motion of physical models of strings that control sound parameters. The two devices control both synthesis parameters and spatialisation parameters, are based on interactions with graphical interfaces, and use specific controllers.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849167
Zenodo URL: https://zenodo.org/record/849167
2004.13
Expressive Gestural Control of Sound and Visual Output in Multimodal Interactive Systems
Camurri, Antonio InfoMus Lab, Università di Genova; Genova, Italy
Mazzarino, Barbara InfoMus Lab, Università di Genova; Genova, Italy
Volpe, Gualtiero InfoMus Lab, Università di Genova; Genova, Italy
Abstract
This paper discusses a multilayered model for strategies for real-time expressive control of sound and visual output. A particular focus is on multimodal interactive systems for performing arts as user-centred systems able to interpret the high-level information conveyed by performers through their expressive gestures and to establish an effective dialog with them taking into account expressive, emotional, affective content. Two kinds of control strategies are discussed enabling the designer of a performance to develop interactive systems able to react to performers’ expressive actions, to build a dialog with performers, or to mix purely reactive behaviour with more complex dialogical situations. A further layer of processing allows dynamic adaptation of control strategies to the evolution of the performance. A quick survey of algorithms for expressive gesture processing is also provided. Expressive gestural control strategies are described with reference to current and past research projects at the DIST- InfoMus Lab. Some concrete applications based on the EyesWeb open platform (www.eyesweb.org) are presented as well.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849171
Zenodo URL: https://zenodo.org/record/849171
2004.14
Expressiveness Detection of Music Performances in the Kinematics Energy Space
Mion, Luca CSC, Department of Information Engineering, Università di Padova; Padova, Italy
De Poli, Giovanni CSC, Department of Information Engineering, Università di Padova; Padova, Italy
Abstract
An experiment for the automatic detection of expressiveness in music performances using a perceptive based auditory models is presented. We recognize the intentions with reference to the Kinematics Energy expressive space. Audio features have been firstly extracted using a perceptionbased analysis, then we have made several analyses on timing and spectral features over overlapping sliding windows, estimating average and variance for each one of the features. Using a naive Bayesian classifier we investigated which features are most relevant for expression detection. This experiment also yielded interesting contributions for tuning the Kinematics Energy space with new features.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849173
Zenodo URL: https://zenodo.org/record/849173
2004.15
Extending a Network-of-elaborations Representation to Polyphonic Music: Schenker and Species Counterpoint
Marsden, Alan Department of Music, Lancaster University; Lancaster, United Kingdom
Abstract
A system of representing melodies as a network of elaborations has been developed, and used as the basis for software which generates melodies in response to the movements of a dancer. This paper examines the issues of extending this representation system to polyphonic music, and of deriving a structural representation of this kind from a musical score. The theories of Heinrich Schenker and of Species Counterpoint are proposed as potentially fruitful bases.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849175
Zenodo URL: https://zenodo.org/record/849175
2004.16
Gestural Control of Singing Voice, a Musical Instrument
Kessous, Loïc Laboratoire de Mécanique et d'Acoustique (LMA); Marseille, France
Abstract
This paper describes research and experiments concerning digital musical instruments based on gestural control of singing voice synthesis. The purpose is to choose and use a two-handed control, a synthesis model and an adequate mapping strategy to allow an expressive pitch control and the articulation of the vowels. A visual feedback is provided to help the performer. By using different models, different aspects of synthetic singing voice as naturalness, expressiveness and vocal identity are explored in relation with gestural control. Several controllers have been tested to achieve a choice of controllers for the musical functionalities needed in this instrument.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849177
Zenodo URL: https://zenodo.org/record/849177
2004.17
IanniX Aesthetical/Symbolic Visualisations for Hypermedia Compositions
Coduys, Thierry La Kitchen, Independent; Paris, France
Ferry, Guillaume La Kitchen, Independent; Paris, France
Abstract
IanniX proposes a graphical representation of a multidimensional and multi-formal score, a kind of poly-temporal meta-sequencer. It allows a multi-topology of the space and relays on the principals of UPIC. IanniX proposes at a macro level of the graphical score a symbolic representation of complex objects still existing in the micro level. The development of IanniX started in 2002, through collaboration between Thierry Coduys (La kitchen), Adrien Lefevre (Adlef), and Gérard Pape (CCMIX). This software continues to privilegiate graphic representation for hypermedia score. An evolution of IanniX is currently under development at La kitchen, bringing new features, especially on aesthetic and graphical customization aspects. Composers can use either GUI (Multiple Document Interface, with direct interactions) or XML scripts directly (advanced edition) to create their scores. IanniX provides network interfaces to communicate with processing software’s (PureData, Max/MSP, SuperCollider, VirChor...) using standard UDP protocol. IanniX is cross-platform software working on Linux, Mac OS or Win32 systems as well. IanniX has been conceived in honour to Iannis Xenakis, conceptor of UPIC. This project is sponsored by the French Ministry of Culture (DMDTS).
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849179
Zenodo URL: https://zenodo.org/record/849179
2004.18
Improvising Computer Music: An Approach
Tarabella, Leonello CNR, Istituto di Scienza e Tecnologie dell’Informazione "A. Faedo" (ISTI); Pisa, Italy
Abstract
I describe here my experience in interactive and improvised electro-acoustic music after having developed both hardware and software tools using which I compose and perform music. The research in the whole finds the roots in my active involvement in jazz music. This paper analyses the jazz approach to improvisation in terms of the involved components and emphasizes the importance of expressiveness and feeling in live performance. Then it proposes a schematic approach to improvising computer music, which gives musicians the same expressive approach, found in jazz, in the new electro-acoustic domain. Two different original gesture recognition devices and systems are described together with a real-time music language, or better, framework based on C-language for sound synthesis and event management. The role of mapping is proposed as crucial and peculiar of the new approach.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849181
Zenodo URL: https://zenodo.org/record/849181
2004.19
IMUTUS -- an Interactive Music Tuition System
Fober, Dominique GRAME - Générateur de Ressources et d’Activités Musicales Exploratoires; Lyon, France
Letz, Stéphane GRAME - Générateur de Ressources et d’Activités Musicales Exploratoires; Lyon, France
Orlarey, Yann GRAME - Générateur de Ressources et d’Activités Musicales Exploratoires; Lyon, France
Abstract
IMUTUS is a European project that aims at the development of an open platform for training students on non MIDI musical instruments, as well as to acquire theoretical music knowledge. The project involves many components oriented towards a new approach of music learning. After a brief overview of the system, the performance evaluation module and the music score processing components are described to show how they enforce the pedagogical approach.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: Missing
Zenodo URL: Missing
2004.20
Influence of Musical Similarity on Melodic Segmentation: Representations and Algorithms
Cambouropoulos, Emilios Department of Music Studies, Aristotle University of Thessaloniki; Thessaloniki, Greece
Tsougras, Costas Department of Music Studies, Aristotle University of Thessaloniki; Thessaloniki, Greece
Abstract
In this paper a computational model is presented that extracts patterns from a given melodic surface and, then, following the assumption that the beginning and ending points of 'significant' repeating musical patterns influence the segmentation of a musical surface, the discovered patterns are used as a means to determine probable segmentation points of the melody. ‘Significant’ patterns are defined primarily in terms of frequency of occurrence and pattern length. The special status of non-overlapping immediately repeating patterns is examined. All the discovered patterns merge into a single ‘pattern’ segmentation profile that signifies points in the surface that are most likely to be perceived as points of segmentation. The effectiveness of the proposed melodic representations and algorithms is tested against a series of melodic examples.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849183
Zenodo URL: https://zenodo.org/record/849183
2004.21
Interactively Determined Generative Sound Design for Sensate Environments
Beilharz, Kirsty Key Centre of Design Computing and Cognition, The University of Sydney; Sydney, Australia
Abstract
Sensate environments provide a medium for humans to interact with space. This interaction includes ambient/passive triggering, performative artistic interaction and physical sensate spaces used for games and interactive entertainment. This paper examines sonic representations of data (sonification) activated by interaction, shaped by user activities and social environmental behaviours. Generative art forms (genetic algorithms and evolutionary design systems) provide methodologies for creating new material. This paper addresses ways in which generative material can relate to representation and experience in a recognisable construct. The purpose of site-specific generative sound and sonification in intelligent buildings is to provide responsive feedback for human participants: sonic indicators of social activity. The affects of the environment influence the generative process – the number of occupants, busy-ness (motion), environmental measurements (e.g. temperature, position relative to specific locations in the space) or direct controls – proximity to sensor walls, movement on pressure sensitive flooring. An examination of comprehensible correspondences between sonic parameters and socio-spatial behaviour articulates a methodology for sonification. The central concern – to generate sound/music clearly indicative of its social context – is applicable in virtual environments as well as wireless sensate physical spaces. Sensate spaces are growing and cutting-edge phenomena at this time that require constructs for expedient computational processing and meaningful sonification of the vast stream of sensed data.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849187
Zenodo URL: https://zenodo.org/record/849187
2004.22
Jack Audio Server: MacOSX Port and Multi-processor Version
Letz, Stéphane GRAME - Générateur de Ressources et d’Activités Musicales Exploratoires; Lyon, France
Fober, Dominique GRAME - Générateur de Ressources et d’Activités Musicales Exploratoires; Lyon, France
Orlarey, Yann GRAME - Générateur de Ressources et d’Activités Musicales Exploratoires; Lyon, France
Davis, Paul Linux Audio Systems; United States
Abstract
Jack is a low-latency audio server, written for POSIX conformant operating systems such as GNU/Linux. It can connect a number of different applications to an audio device, as well as allowing them to share audio between themselves. We present the port for Apple’s MacOS X, and new developments to take advantage of multi-processor architecture.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849189
Zenodo URL: https://zenodo.org/record/849189
2004.23
Logical Representation of Musical Concepts (for Analysis and Composition Tasks Using Computers)
Phon-Amnuaisuk, Somnuk Multimedia University; Cyberjaya, Malaysia
Abstract
The main activities in music studies concern defining structures and studying relationships among them. Computers could be very useful in performing these tasks. This paper discusses the representation of musical concepts for reasoning tasks which are common in the analysis and composition of musical works. We argue in favour of the following properties in our representation framework: abstraction, expressiveness, multiple views and reasoning efficiency. Then we discuss some examples of the reasoning tasks based on the proposed representation structure. A harmonisation example produced using the framework discussed is given to illustrate our points.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849191
Zenodo URL: https://zenodo.org/record/849191
2004.24
Melody Classification Using a Similarity Metric Based on Kolmogorov Complexity
Li, Ming School of Computing Sciences, University of East Anglia (UEA); Norwich, United Kingdom
Sleep, Ronan School of Computing Sciences, University of East Anglia (UEA); Norwich, United Kingdom
Abstract
Vitanyi and his co-workers [5] have reported some success using a universal similarity metric based on Kolmogorov complexity for a variety of classification tasks, including music genre recognition. This paper describes new experiments in this direction, and compares the results with some alternative approaches. Somewhat to our surprise given its non-specific universal nature, the Kolmogorov complexity similarity based technique outperformed the others. The task used for our experiments involved classification of MIDI files into one of 4 groups. Two of the categories were western classical music composed by Beethoven (302 files) and Haydn (261 files). The remaining categories were Chinese music (80 files) and Jazz (128 files). Melody contours (i.e. pitch sequences without timing details) were extracted from the MIDI file tracks. Both relative and absolute and pitch contours were used. The best performance of 92.35\% was achieved by a 1-nearest neighbour classifier with normalized information distance based on Kolmogorov complexity estimates over pitch interval contours. A notable feature of our work is the use of the number of blocks in a pure Lempel-Zip parse of a string to estimate its Kolmogorov complexity.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849193
Zenodo URL: https://zenodo.org/record/849193
2004.25
Music Retrieval Algorithms for the Lead Sheet Problem
Clifford, Raphaël Algorithm Design Group, Department of Computer Science, King's College London; London, United Kingdom
Groult, Richard LIFAR, Université de Rouen Normandie; Mont-Saint-Agnan, France
Iliopoulos, Costas S. Algorithm Design Group, Department of Computer Science, King's College London; London, United Kingdom
Byrd, Donald School of Music, Indiana University Bloomington; Bloomington, United States
Abstract
Methods from string and pattern matching have recently been applied to many problems in music retrieval. We consider the so-called lead sheet problem, where the harmony, melody, and, usually, bass line are presented separately. This is a common situation in some forms of popular music but is also significant for ”classical” music in many cases. A number of different but related musical situations are analysed and efficient algorithms are presented for music retrieval in each one.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849195
Zenodo URL: https://zenodo.org/record/849195
2004.26
New Approaches of Theatre and Opera Directly Inspired by Interactive Data-mining
Bonardi, Alain University Paris VIII; Saint-Denis, France
Rousseaux, Francis Institut de Recherche et Coordination Acoustique/Musique (IRCAM); Paris, France
Abstract
In this paper, we show to what extent traditional theatre staging is based on a formal approach of similarity using a dramaturgical ontology and instanciation variations. Drawing our inspiration from the opposite approach through interactive data mining, we hereby account for theatre and opera researches using computers as actor partners to escape a priori specification.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849197
Zenodo URL: https://zenodo.org/record/849197
2004.27
On Onsets On-the-fly: Real-time Event Segmentation and Categorisation as a Compositional Effect
Collins, Nick Centre for Music and Science, Faculty of Music, University of Cambridge; Cambridge, United Kingdom
Abstract
Compositional applications for real-time event segmentation are discussed. A causal real-time onset detector which makes onset data available as fast as possible is introduced, based on work by Klapuri, Hainsworth and Jensen and Andersen. This analysis frontend informs algorithmic cutting procedures which respect the events of the incoming audio stream. A further refinement stores events to particular buffers based on a coarse categorisation between snare, kick or hihat classes. Algorithmic composers running playback of these buffers thereby respond to changing timbral events of a live feed from an instrumentalist or other audio source. The use of an onset detection threshold to create abstracted rhythms based on some existing source is further examined.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849199
Zenodo URL: https://zenodo.org/record/849199
2004.28
Open Source Tools for Music Representation and Notation
Fober, Dominique GRAME - Générateur de Ressources et d’Activités Musicales Exploratoires; Lyon, France
Letz, Stéphane GRAME - Générateur de Ressources et d’Activités Musicales Exploratoires; Lyon, France
Orlarey, Yann GRAME - Générateur de Ressources et d’Activités Musicales Exploratoires; Lyon, France
Abstract
Although numerous systems and applications exist for music representation and graphic notation, there are few resources available to developers. We present two open source projects that aim at making up for this lack of components: the MusicXML library, intended to support the MusicXML format and to provide music notation exchange capabilities, and the GUIDO library that provides a powerful graphic score engine, based on the GUIDO music notation format.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849201
Zenodo URL: https://zenodo.org/record/849201
2004.29
Pattern Anchoring, Identity and Signatures in Sound, Time and Space
İzmirli, Özgür Ammerman Center for Arts and Technology, Connecticut College; New London, United States
Zahler, Noel School of Music, University of Minnesota; Minneapolis, United States
Abstract
The process of score following requires that the automated follower be capable of making robust decisions during a performance, especially in light of the number of errors that need to be accounted for between the live performer and the follower. Based on the idea of variable-length signatures for monophonic input we define a causal method for tracking location in score following. The signatures and their lengths are calculated prior to performance based on their novelty in a predetermined locality within the score. Results are shown using a graphical display that depicts the associations, determined by a score follower, between performed notes and the score. This display aids in visual evaluation of the performance of the score following process and specifically its capability of recovery following any of the performance aberrations.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849203
Zenodo URL: https://zenodo.org/record/849203
2004.30
Physical Modeling for Pure Data (pmpd) and Real Time Interaction With an Audio Synthesis
Henry, Cyrille La Kitchen, Independent; Paris, France
Abstract
This article describes an application of physical modeling tools for pure data (pd) for real time interaction between a musician and an audio synthesis. pmpd is a collection of objects for pd providing a very flexible way to particle physical modeling simulation and other kind of comportment-based modelling. pmpd is used for data generation. That is to say that, although they can easily be used to control audio engines, they do not generate audio signals directly. Virtual physical structure can act as a black box between the musician and the audio synthesis. Using pmpd within the pd programming environment allows real-time interactions with this simulation, as well as natural control of a sound. A musician can play with the movement of a virtual structure, which produces sound.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849205
Zenodo URL: https://zenodo.org/record/849205
2004.31
Physical Modeling of Impacts: Theory and Experiments on Contact Time and Spectral Centroid
Avanzini, Federico CSC, Department of Information Engineering, Università di Padova; Padova, Italy
Rocchesso, Davide Department of Computer Science, Università di Verona; Verona, Italy
Abstract
A model for physically based synthesis of collision sounds is discussed. Attention is focused on the properties of the non-linear contact force, and on the influence of the physical parameters on the perceptually salient sound features. First, the dependence of the contact time on the force parameters is established analytically and validated through numerical simulations. Then, the relation with the timevarying spectral centroid is discussed. As a result, a mapping between the physical parameters of the impact force and the acoustic parameters of the impact sound is proposed.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849207
Zenodo URL: https://zenodo.org/record/849207
2004.32
Playing Integrated Music Knowledges With Artifical Neural Networks
Voisin, Frédéric Centre National de Creation Musicale (CIRM); Nice, France
Meier, Robin Centre National de Creation Musicale (CIRM); Nice, France
Abstract
This text presents some aspects of the Neuromuse project developed at CIRM. We will present some experiences in using self-organizing maps (SOM) to generate meaningful musical sequences, in realtime interfaces, with MaxMSP and Jitter3.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849209
Zenodo URL: https://zenodo.org/record/849209
2004.33
PWGL Editors: 2D-editor as a Case Study
Laurson, Mikael Sibelius Academy, University of the Arts Helsinki; Helsinki, Finland
Kuuskankare, Mika Sibelius Academy, University of the Arts Helsinki; Helsinki, Finland
Abstract
This paper presents some of the main concepts behind PWGL editors. PWGL is an OpenGL based visual programming language specialized in computer aided composition and sound synthesis. Editors have a central role in PWGL as they allow to investigate and manipulate complex objects. We first describe some of the general design issues behind PWGL editors. We will use one of the main editors, the 2D-editor, as a case study. The 2D-editor allows to combine and synchronize visually various 2Dobjects within one editor.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849213
Zenodo URL: https://zenodo.org/record/849213
2004.34
Recent Developments in ENP-score-notation
Kuuskankare, Mika Sibelius Academy, University of the Arts Helsinki; Helsinki, Finland
Laurson, Mikael Sibelius Academy, University of the Arts Helsinki; Helsinki, Finland
Abstract
In this paper we describe the recent developments on a text-based score representation format called ENP-scorenotation. ENP-score-notation is used to describe scores in Expressive Notation Package (ENP). We introduce the basic concepts behind ENP-score-notation and discuss several new features in detail along with some notational examples. We also examine some syntactic changes and point out the differences between the new and the old syntax. Furthermore, we propose a new interface to PWGL, including several new boxes, which allows to use ENPscore-notation to construct musical objects in a PWGL patch.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849215
Zenodo URL: https://zenodo.org/record/849215
2004.35
Regards on Two Regards by Messiaen: Automatic Segmentation Using the Spiral Array
Chew, Elaine Integrated Media Systems Center, Viterbi School of Engineering, University of Southern California; Los Angeles, United States
Abstract
Segmentation by pitch context is a fundamental process in music cognition, and applies to both tonal and atonal music. This paper introduces a real-time, O(n), algorithm for segmenting music automatically by pitch collection using the Spiral Array model. The segmentation algorithm is applied to Olivier Messiaen’s Regard de la Vierge (Regard IV) and Regard des prophètes, des bergers et des Mages (Regard XVI) from his Vingt Regards sur l’Enfant Jésus. The algorithm uses backward and forward windows at each point in time to capture local pitch context in the recent past and not-too-distant future. The content of each window is mapped to a spatial point, called the center of effect (c.e.), in the interior of the Spiral Array. The distance in the Spiral Array space between the c.e.’s of each pair of forward and backward windows measures the difference in pitch context between the future and past segments at each point in time. Segmentation boundaries then correspond to peaks in these distance values. This paper explores and analyzes the algorithm’s segmentation of post-tonal music, namely, Messiaen’s two Regards, using various window sizes. The computational results are compared to manual segmentations of the pieces. Taking into account the entire piece, the best case computed boundaries are, on average, within 0.94% (for
Regard IV) and 0.11\% (for Regard XVI) of their targets.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849217
Zenodo URL: https://zenodo.org/record/849217
2004.36
Sim - Système Interactif Musical (Cybersongosse 7mi)
Clozier, Christian Institut international de musique électroacoustique de Bourges (IMEB); Bourges, France
Le Duc, Jean-Claude Institut international de musique électroacoustique de Bourges (IMEB); Bourges, France
Mihalic, Alexander Institut international de musique électroacoustique de Bourges (IMEB); Bourges, France
Abstract
Over the last thirty years, the International Institute of Electroacoustic Music of Bourges - "IMEB" has been developing music-related educational concepts and building a unique and original instrument named "Gmebogosse" then "Cybersongosse". This one-of-a-kind instrument designed to create sounds and electroacoustic music with easy manual control binds together a range of classic "studio" modules: recording, synthesis, effects, mixing and spatialized output... Being analogue at first, it has now turned into a fully digital workstation while retaining its playability and ease of use.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849221
Zenodo URL: https://zenodo.org/record/849221
2004.37
Soliloque Sur [X, X, X et X], Musical Commentaries From a Computer About a Concert Misunderstood by It
Lévy, Fabien Conservatory of Berlin; Berlin, Germany
Seelig, Thomas Electronic Music Studio, Technische Universität Berlin (TU Berlin); Berlin, Germany
Abstract
To compose a composer... Soliloque sur [X, X, X et X]1 is not just a musical work, but more a meta-score, generated by the computer in real-time from other works of the concert. It means that for every concert, the generated work is different, in its sounds as well as in its organization. This computer application also requires a particular real-time technology, because it involves changing a signal processing network "on the fly" without sound interruption.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849223
Zenodo URL: https://zenodo.org/record/849223
2004.38
Specification of Temporal Relations Between Interactive Events
Desainte-Catherine, Myriam University Bordeaux I; Bordeaux, France
Allombert, Antoine University Bordeaux I; Bordeaux, France
Abstract
We propose a formalism for specifying temporal relations between interactive triggerings and releasings occurring during performance of written musical pieces. Temporal durations are specified between parts or notes of a written piece. Then, we proceed to a static analysis of the piece in order to produce a program providing safe execution of the piece according to the temporal relations.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849225
Zenodo URL: https://zenodo.org/record/849225
2004.39
Strategies for Continuous Pitch and Amplitude Tracking in Realtime Interactive Improvisation Software
Dobrian, Christopher Department of Music, University of California, Irvine; Irvine, United States
Abstract
In a realtime interactive work for live performer and computer, the immanently human musical expression of the live performer is not easily equalled by algorithmically generated artificial expression in the computer sound. In cases when we expect the computer to display interactivity in the context of improvisation, pre-programmed emulations of expressivity in the computer are often no match for the charisma of an experienced improviser. This article proposes to achieve expressivity in computer sound by “stealing” expressivity from the live performer. By capturing, analyzing, and storing expressive characteristics found in the audio signal received from the acoustic instrument, the computer can use those same characteristic expressive sound gestures, either verbatim or with modifications. This can lead to a more balanced sense of interactivity in works for live performer and computer.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849227
Zenodo URL: https://zenodo.org/record/849227
2004.40
Style Recognition Through Statistical Event Models
Pérez-Sancho, Carlos Department of Language and Computer Systems, Universidad de Alicante; Alicante, Spain
Iñesta, José Manuel Department of Language and Computer Systems, Universidad de Alicante; Alicante, Spain
Calera-Rubio, Jorge Department of Language and Computer Systems, Universidad de Alicante; Alicante, Spain
Abstract
The automatic classification of music fragments into styles is one challenging problem within the music information retrieval (MIR) domain and also for the understanding of music style perception. This has a number of applications, including the indexation and exploration of music databases. Some technologies employed in text classification can be applied to this problem. The key point here is to establish something in music equivalent to the words in texts. A number of works use the combination of intervals and duration ratios for this purpose. In this paper, different statistical text recognition algorithms are applied to style recognition using this kind of melody representation, exploring and comparing their performance for different word sizes.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849229
Zenodo URL: https://zenodo.org/record/849229
2004.41
The AGNULA/DeMuDi Distribution: GNU/linux and Free Software for the Pro Audio and Sound Research Domain
Bernardini, Nicola Media Innovation Unit, Firenze Tecnologia; Firenze, Italy
Cirotteau, Damien Media Innovation Unit, Firenze Tecnologia; Firenze, Italy
Ekanayaka, Free Media Innovation Unit, Firenze Tecnologia; Firenze, Italy
Glorioso, Andrea Media Innovation Unit, Firenze Tecnologia; Firenze, Italy
Abstract
AGNULA (acronym for “A GNU/Linux Audio distribution”, pronounced with a strong g) is the name of a project which has been funded until April 2004 by the European Commission (number of contract: IST-2001-34879; key action IV.3.3, Free Software: towards the critical mass). After the end of the funded period, AGNULA is continuing as an international, mixed volunteer/funded project, aiming to spread Free Software in the professional audio/video arena. The AGNULA team is working on a tool to reach this goal: AGNULA/DeMuDi, a GNU/Linux distribution based on Debian, entirely composed of Free Software, dedicated to professional audio research and work. This paper describes the current status of AGNULA/DeMuDi and how the AGNULA team envisions future work in this area.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849231
Zenodo URL: https://zenodo.org/record/849231
2004.42
The Realtime-score. A Missing-link in Computer-music Performance
Winkler, Gerhard E. Composer, Independent; Salzburg, Austria
Abstract
Between the realms of improvisation and the execution of a paper-written, fixed score the concept of RealtimeScore opens a kind of "Third Way" of interpretation. It is based on the idea, that the score for one or more musicians playing on stage is generated in realtime during a performance and projected directly on a computerscreen which is placed before the musicians like a traditional note-stand. The musicians can interactively influence the evolution of the piece (based on simulations of complex dynamic systems), so that each performance is a unique realisation of a piece. The text will introduce the concept and discuss linked topics like notation, interaction, interpretation, audiance, and the role of the composer in this new concept.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849233
Zenodo URL: https://zenodo.org/record/849233
2004.43
Three-dimensional Gestural Controller Based on Eyecon Motion Capture System
Merlier, Bertrand Department of Music, University Lumière Lyon 2; Lyon, France
Abstract
This article presents a new gestural computer interface (3DGC = Three-Dimensional Gestural Controller) allowing an instrument-like complex control. Hand gestures are analyzed by means of a camera and by a motion capture software. Contrary to classical instrument interfaces, neither any mechanical organ nor any mark is visible! This concept offers important freedom of gestural control in any 3 dimensions of space. However it requires reconsidering the relation between cause and effect, i.e. between gesture and sound result. We shall present several specific features linked to lack of any visual mark or mechanical constraints. Then we shall underline the interest of programmability and simultaneous control of several parameters in only one simple gesture. First use of 3DGC is to control generation, transformation and spatialization of live electroacoustic music. Many other artistic applications are imaginable in the multimedia area, such as live video pictures generation and transformation. The "4 Hands" project - an instrumental multimedia duet uses two 3DGC for live sound and video creation. It was presented at Ars Electronica Festival (Linz - Austria) i n September 2002.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849235
Zenodo URL: https://zenodo.org/record/849235
2004.44
Tying Semantic Labels to Computational Descriptors of Similar Timbres
Fitzgerald, Rosemary A. Department of Music, Lancaster University; Lancaster, United Kingdom
Lindsay, Adam T. Department of Computing, Lancaster University; Lancaster, United Kingdom
Abstract
This paper asserts the importance of using multiple representations when examining computational descriptions of any musical percept. We examine the existing stateof-the-art among the MPEG-7 timbre descriptors, and by choosing oboe timbre as our domain we investigate their application to timbres from the same instrument. Using a dual approach, correlating perceptual information with a wide range of computational descriptors, we propose potential extensions to MPEG-7 representations. By eliminating the need for generality across instruments, we believe we can reach a higher level of semantic representation within timbre domains from a single instrument class.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849237
Zenodo URL: https://zenodo.org/record/849237
2004.45
Understanding Expressive Transformations in Saxophone Jazz Performances Using Inductive Machine Learning
Ramirez, Rafael Music Technology Group (MTG), Pompeu Fabra University (UPF); Barcelona, Spain
Hazan, Amaury Music Technology Group (MTG), Pompeu Fabra University (UPF); Barcelona, Spain
Gómez, Emilia Music Technology Group (MTG), Pompeu Fabra University (UPF); Barcelona, Spain
Maestre, Esteban Music Technology Group (MTG), Pompeu Fabra University (UPF); Barcelona, Spain
Abstract
In this paper, we describe an approach to learning expressive performance rules from monophonic Jazz standards recordings by a skilled saxophonist. We have first developed a melodic transcription system which extracts a set of acoustic features from the recordings producing a melodic representation of the expressive performance played by the musician. We apply machine learning techniques to this representation in order to induce rules of expressive music performance. It turns out that some of the induced rules represent extremely simple principles which are surprisingly general.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849239
Zenodo URL: https://zenodo.org/record/849239
2004.46
Using Patterns to Generate Rhythmic Accompaniment for Guitar
Dahia, Marcio Center of Informatics, Federal University of Pernambuco; Recife, Brazil
Santana Ernesto Trajano, Hugo Center of Informatics, Federal University of Pernambuco; Recife, Brazil
Ramalho, Geber Center of Informatics, Federal University of Pernambuco; Recife, Brazil
Sandroni, Carlos Department of Music, Federal University of Pernambuco; Recife, Brazil
Cabral, Giordano Laboratoire d'Informatique de Paris 6 (LIP6), Université Paris 1 Panthéon-Sorbonne; Paris, France
Abstract
This work presents the model of a system that generates guitar rhythmic accompaniment of a song, given its chord grid and melody. In order to minimize the effects of the lack of formal knowledge which inherently exists in this musical dimension, the system uses a very natural approach in music: the contextualized reuse of rhythmic patterns, found in performances of famous musicians. To accomplish this task, two techniques of artificial intelligence were combined: case-based reasoning, for the modeling the "musical memory" (association of rhythmic patterns and the context where it should be used) and rule-based reasoning, to associate abstract intentions to the contextual characteristics of the patterns. As a case study, we developed Cyber-João, a program that generates a rhythmic accompaniment for Bossa Nova by chaining and adapting rhythmic patterns found in classic records of João Gilberto. Finally, the model was empirically compared with some other approaches implemented to solve the problem, demonstrating very motivating results.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849241
Zenodo URL: https://zenodo.org/record/849241
2004.47
Virtual Voices on Hands: Prominent Applications on the Synthesis and Control of the Singing Voice
Georgaki, Anastasia Department of Music, National and Kapodistrian University of Athens; Athens, Greece
Abstract
The on-going research of the last thirty years on the synthesis of the singing voice highlights different aspects of this implicative field which involves the interdisciplinary area of musical acoustics, signal processing, linguistics, artificial intelligence, music perception and cognition, music information retrieval and performance systems. Recent work shows that the musical and natural quality of singing voice synthesis has evolved enough for high fidelity commercial applications to be realistically envisioned. In the first paragraph of this paper we are going to highlight briefly the different aspects of the on-going research (synthesis models, performance by rules, textto- speech synthesis, controllers) through a taxonomy of these approaches. In the second part we are going to emphasize on the utility and the different applications of this research area (including the recent commercial ones) as a tool for the music creativity by presenting audio and video excerpts of various approaches through a MIDI accordion. Finally, we are going to present future and related work on Greek singing, outlining a new research project named ΑOIDOS /Virtual Greek singer which is under development at the University of Athens. By this article we want to highlight the prominent applications of this research domain in the field of musicology and music creation and music education.
Keywords
not available
Paper topics
not available
Easychair keyphrases
not available
Paper type
unknown
DOI: 10.5281/zenodo.849243
Zenodo URL: https://zenodo.org/record/849243