The Virtual World of Cerberus: Virtual Singer using Spike-Timing-Dependent Plasticity Concept

The Virtual World of Cerberus: Virtual Singer using Spike-Timing-Dependent Plasticity Concept

Jocelyne Kiss (LISAA, University Paris East, France), Sidi Soueina (Strayer University, USA), Martin Laliberté (LISAA, University Paris East, France) and Adel Elmaghraby (University of Louisville, USA)
DOI: 10.4018/978-1-60960-077-8.ch009
OnDemand PDF Download:
No Current Special Offers


While exploring autonomous evolution concepts for virtual worlds, we will present a new design Cerberus an avatar singer who can accompany a singer, perform alone and make his song evolves using simple past events. This 3D interactive facial animated avatar was made thanks to virtools software. The main originality of Cerberus is to develop his own melody by using learning machines and constantly improve his musical style and emotions. Cerberus is implemented using competitive learning rules to trained artificial neural networks in order to perform these self-improvements. Self-improvements is a key of our learning capacity, The challenge of building a virtual singer that could promotes his own improvisation is an open research field (Minsky, 2000).We will expose the difficulties of the synchronization in real-time between the voice and animation to generate the right emotion, also the difficulties of establishing a classification which could be in contradiction with the ontology of the musical fact. Also we will expose the necessity of developing avatars that use the amazing potentialities of spike-timing-dependent plasticity concept (Abraham, & Bear, 1996), that hence metaplasticity. This powerful concept enhance the potentiality of avatar design and give the impression that the avatar has a memory and simulate “feelings” linked to a context.
Chapter Preview

Problem Analysis

If we consider a simulation of a robot mimicking a singing gesture as mediating function between the actual act of singing and a more abstract to find inspiration using past events, is providing both a symbolic vocabulary and ideal objects, then it seems that it stands out as an effective way to know or even understand some of the music creation process (Barbaud, 1966). The main difficulty of such a system is the balance of shares that must be given to peculiarities inherent in this creation and the necessary generalization. As sketched out a first issue regarding the orientation of the program because it would, indeed utopian in the current research, as demonstrated in previous experiments Consider a system capable of generating imposed in a context, a complex musical phenomenon, regardless of any arbitrary choice beforehand. How then implement a decision unit capable of directing the genesis of an avatar engine?

Automated systems possess two qualities: the ability to deal quickly at the micro-compositional level, and that of acquiring a unit by the expression of certain 'musical intentions' (Miranda & Matthias, 2009). A singing avatar should have the abilities to “listen” to the proposition, to her public and to sing and improvise by itself. This virtual singer will is presented in the form of a visual interface to avatar 3D in order to articulate a phoneme while producing a sound (DiPaola, 1989). The main difficulty is to provide a real-time system which could evolve by itself, and simulate an accurate articulation and facial expression and a sound. Naturally, synthesis voice technical is used (it would be very difficult and time consuming to use prerecorded sound using pattern matching method, (Efrat & al. 2004)). Also it seems that the first step will be to use an artificial neural network in order to manage the recognition of the events. It should be able to manage an “artistic choice”.

Figure 1.

Cerberus performing


Complete Chapter List

Search this Book: