Bruno Gas

A New Nonlinear speaker parameterization algorithm for speaker identification

Mohamed Chétouani, Marcos Faúndez-Zanuy, Bruno Gas, Jean‐Luc Zarader

In this paper we propose a new parameterization algorithm based on nonlinear prediction, which is an extension of the classical LPC parameters. The parameters performances are estimated by two different methods: the Arithmetic-Harmonic Sphericity (AHS) and the Auto-Regressive Vector Model (ARVM). Two …

fr (code pays fourni par la source)

A New Nonlinear speaker parameterization algorithm for speaker\n identification

Mohamed Chétouani, Marcos Faúndez-Zanuy, Bruno Gas, Jean‐Luc Zarader

In this paper we propose a new parameterization algorithm based on nonlinear\nprediction, which is an extension of the classical LPC parameters. The\nparameters performances are estimated by two different methods: the\nArithmetic-Harmonic Sphericity (AHS) and the Auto-Regressive Vector Model\n(ARVM). Two different methods are proposed …

A Formal Account of Structuring Motor Actions With Sensory Prediction for a Naive Agent

Jean-Merwan Godon, Sylvain Argentieri, Bruno Gas

For naive robots to become truly autonomous, they need a means of developing their perceptive capabilities instead of relying on hand crafted models. The sensorimotor contingency theory asserts that such a way resides in learning invariants of the sensorimotor flow. We propose …

fr (code pays fourni par la source)

Bootstrapping perception with action: a case for sensory prediction

Jean Jaques Godon, Sylvain Argentieri, Bruno Gas

Audition as a Trigger of Head Movements

Benjamin Cohen-Lhyver, Sylvain Argentieri, Bruno Gas

fr (code pays fourni par la source)

Where Do I Move My Sensors? Emergence of a Topological Representation of Sensors Poses From the Sensorimotor Flow

Valentin Marcel, Sylvain Argentieri, Bruno Gas

This article deals with the perception of mobile robotic systems within the framework of interactive perception, and inspired by the sensorimotor contingencies (SMCs) theory. These approaches state that perception arises from the active exploration of an environment. In the SMC theory, it …

fr (code pays fourni par la source)

Audition as a Trigger of Head Movements

Benjamin Cohen-Lhyver, Sylvain Argentieri, Bruno Gas

In multimodal realistic environments, audition and vision are the prominent two sensory modalities that work together to provide us with a best possible understanding of the perceptual contents of the world. Yet, when designing artificial binaural systems, this collaboration often not honored. …

A Non-linear Approach to Space Dimension Perception by a Naive Agent

Alban Laflaquière, Sylvain Argentieri, Olivia Breysse, Stéphane Genet et autres

Developmental Robotics offers a new approach to numerous AI features that are often taken as granted. Traditionally, perception is supposed to be an inherent capacity of the agent. Moreover, it largely relies on models built by the system's designer. A new approach …

fr (code pays fourni par la source)

Learning an internal representation of the end-effector configuration space

Alban Laflaquière, A. V. Terekhov, Bruno Gas, John O'Regan

Current machine learning techniques proposed to automatically discover a robot kinematics usually rely on a priori information about the robot's structure, sensors properties or end-effector position. This paper proposes a method to estimate a certain aspect of the forward kinematics model with …

fr (code pays fourni par la source)

Learning an internal representation of the end-effector configuration space

Alban Laflaquière, Alexander V. Terekhov, Bruno Gas, John O'Regan

Current machine learning techniques proposed to automatically discover a robot kinematics usually rely on a priori information about the robot's structure, sensors properties or end-effector position. This paper proposes a method to estimate a certain aspect of the forward kinematics model with …

fr (code pays fourni par la source)

Learning agent's spatial configuration from sensorimotor invariants

Alban Laflaquière, John O'Regan, Sylvain Argentieri, Bruno Gas et autres

The design of robotic systems is largely dictated by our purely human intuition about how we perceive the world. This intuition has been proven incorrect with regard to a number of critical issues, such as visual change blindness. In order to develop …

fr (code pays fourni par la source)

The Head Turning Modulation System: An Active Multimodal Paradigm for Intrinsically Motivated Exploration of Unknown Environments

Benjamin Cohen-Lhyver, Sylvain Argentieri, Bruno Gas

Over the last 20 years, a significant part of the research in exploratory robotics partially switches from looking for the most efficient way of exploring an unknown environment to finding what could motivate a robot to autonomously explore it. Moreover, a growing …

fr (code pays fourni par la source)