Sigma-Lognormal Modeling of Speech.

Human movement studies and analyses have been fundamental in many scientific domains, ranging from neuroscience to education, pattern recognition to robotics, health care to sports, and beyond. Previous speech motor models were proposed to understand how speech movement is produced and how the resulting speech varies when some parameters are changed. However, the inverse approach, in which the muscular response parameters and the subject's age are derived from real continuous speech, is not possible with such models. Instead, in the handwriting field, the kinematic theory of rapid human movements and its associated Sigma-lognormal model have been applied successfully to obtain the muscular response parameters. This work presents a speech kinematics-based model that can be used to study, analyze, and reconstruct complex speech kinematics in a simplified manner. A method based on the kinematic theory of rapid human movements and its associated Sigma-lognormal model are applied to describe and to parameterize the asymptotic impulse response of the neuromuscular networks involved in speech as a response to a neuromotor command. The method used to carry out transformations from formants to a movement observation is also presented. Experiments carried out with the (English) VTR-TIMIT database and the (German) Saarbrucken Voice Database, including people of different ages, with and without laryngeal pathologies, corroborate the link between the extracted parameters and aging, on the one hand, and the proportion between the first and second formants required in applying the kinematic theory of rapid human movements, on the other. The results should drive innovative developments in the modeling and understanding of speech kinematics.

Studying the variability of handwriting patterns using the Kinematic Theory.

The variability observed in handwriting patterns is analyzed from the perspective of integrating the resulting motor control knowledge in the design of more powerful handwriting recognizers in personal digital assistants (PDAs) and smartphones. Using the highest representational level of the Kinematic Theory of Rapid Human Movement, the Sigma-Lognormal model, this article reports basic theoretical and practical results that could be taken into account in the design of such systems. The main movement variability introduced by the neuromuscular system (NMS) and induced through the scheduling of motor tasks by the central nervous system (CNS) is divided into global and local fluctuations. From a fiducial action plan decoded by this model, a wide range of handwriting distortions are artificially generated by acting on the Sigma-Lognormal parameters. The resulting patterns are studied to understand scale changes and rotational deformations, the two basic features that a recognizer has to take into account. An experiment based on the writing of the same word by six writers is also reported. The results, obtained by an ANOVA analysis, corroborate the predictions and support the relevance of the Kinematic Theory for the analysis and synthesis of handwriting disruptions. These findings consolidate the results of previous studies on single strokes using the Sigma-Lognormal model. Overall, this report provides new insights into our understanding of motor control, as well as into practical cues for the development of huge databases of letters and words to train and test on-line handwriting classifiers and recognizers.

Stability analysis of bidirectional associative memory networks with time delays.

By using the method of Liapunov functional, a model for bidirectional associative memory networks with time delays is studied. The asymptotic stability is global in the state space of the neuronal activations and is also independent of the delays. Our results can be applied to a variety of situations that arise both in the field of biological and artificial neural networks.

On the stability analysis of delayed neural networks systems.

In this paper, the problems of stability of delayed neural networks are investigated, including the stability of discrete and distributed delayed neural networks. Under the generalization of dropping the Lipschitzian hypotheses for output functions, some stability criteria are obtained by using the Liapunov functional method. We do not assume the symmetry of the connection matrix and we establish that the system admits a unique equilibrium point in which the output functions do not satisfy the Lipschitz conditions and do not require them to be differential or strictly monotonously increasing. These criteria can be used to analyze the dynamics of biological neural systems or to design globally stable artificial neural networks.

The segmentation of cursive handwriting: an approach based on off-line recovery of the motor-temporal information.

This paper presents a segmentation method that partly mimics the cognitive-behavioral process used by human subjects to recover motor-temporal information from the image of a handwritten word. The approach does not exploit any thinning or skeletonization procedure, but rather a different type of information is manipulated concerning the curvature function of the word contour. In this way, it is possible to detect the parts of the image where the original odometric information is lost or ambiguous (such as, for example, at an intersection of the handwritten lines) and interpret them to finally recover a part of the original temporal information. The algorithm scans the word, following the natural course of the line, and attempts to reproduce the same movement as executed by the writer during the generation of the word. It segments the cursive trace where the contour shows the slow-down of the original movement (corresponding to the maximum curvature points of the curve). At the end of the scanning process, a temporal sequence of motor strokes is obtained which plausibly composed the original intended movement.

The 2/3 power law: when and why?

This paper presents the origin of some reported observations, which links the kinematics of handwriting with a movement trajectory, best known as the 2/3 power law. Using computer simulations, it is shown that the vectorial delta-lognormal model recently proposed to describe 2D movements can successfully simulate these phenomena. Although the power law has been found to be a good predictor in many experimental conditions, a few experiments have shown that the law does not apply to all graphic movements. Using the vectorial delta-lognormal model, the conditions under which a 2/3 power relationship can be observed are presented and the reasons why it does not seem to be verified for more general handwritten patterns are highlighted.

A kinematic theory of rapid human movements: Part III. Kinetic outcomes.

This paper describes the kinematic and kinetic properties of simple rapid movements using a single and unique framework based on a delta-lognormal law (Plamondon 1993a,b, 1995a,b). Predictions concerning isotonic measurements are made using the properties of acceleration profiles, as described by the first time derivative of the delta-lognormal law. Predictions dealing with isometric measurements are directly analyzed using the delta-lognormal law, after demonstrating the experimental equivalence between isometric forces and virtual velocity profiles. The theory is also used to make statistical predictions about the variability of numerous kinematic and kinetic variables. The overall approach can be viewed as if, at some level of representation, the central nervous system were planning, executing and evaluating simple rapid movements in terms of momentum and energy instead of forces. The unifying perspective provided by the theory constitutes a powerful tool with which to study and analyze movements under numerous experimental conditions, using a single analytical law.

Human identification of letters in mixed-script handwriting: an upper bound on recognition rates.

This paper focuses on a reading task consisting of the identification of letters in mixed-script handwritten words. This task is performed by humans using extended or limited linguistic context. Their performance rate is to give an upper bound on recognition rates of computer programs designed to recognize handwritten letters in mixed-script writing. Many recognition algorithms are being developed in the research community, and there is a need for establishing ways to compare them. As some effort is on its way to give large test sets with standard formats, we propose an algorithm to determine a test set of reduced size that is appropriate for the task to achieve (the type of texts or words to be recognized). Also, with respect to a particular task, we propose a method for finding an upper limit to the letter recognition rate to aim for.

Extraction of signatures from check background based on a filiformity criterion.

Extracting a signature from a check with a patterned background is a thorny problem in image segmentation. Methods based on threshold techniques often necessitate meticulous postprocessing in order to correctly capture the handwritten information. In this study, we tackle the problem of extracting handwritten information by means of an intuitive approach that is close to human visual perception, defining a topological criterion specific to handwritten lines which we call filiformity. This approach was inspired by the existence in the human eye of cells whose specialized task is the extraction of lines. First, we define two topological measures of filiformity for binary objects. Next, we extend these measures to include gray-level images. One of these measures, which is particularly interesting, differentiates the contour lines of objects from the handwritten lines we are trying to isolate. The local value provided by this measure is then processed by global thresholding, taking into account information about the whole image. This processing step ends with a simple fast algorithm. Evaluation of the extraction algorithm carried out on 540 checks with 16 different background patterns demonstrates the robustness of the algorithm, particularly when the background depicts a scene.

A new method for the analysis of simple and complex planar rapid movements.

Recent developments in the field of simple human movement modelling provide new ways in which to view complete models for analysing and understanding complex movements. Based on a kinematic theory and a vectorial delta-lognormal model recently proposed by Plamondon (1993a); Plamondon (1995a); Plamondon (1995b); Plamondon (1995c) and Plamondon (1998), a new method for exploring and understanding the inherent mechanisms that govern planar movement generation and predict human behaviour is presented here. This paper describes an approach for analysing simple as well as complex movements such as cursive handwriting. It highlights some difficulties encountered in the analysis of complex movements. Problems such as the development of robust approaches to solve the reverse engineering problem of automatic parameter extraction of a succession of time-overlapped nonlinear functions are discussed. The analysis of natural cursive handwriting shows many interesting properties of the model and proposes new ways to study perturbed movement phenomena.

Speed/accuracy trade-offs in target-directed movements.

This target article presents a critical survey of the scientific literature dealing with the speed/accuracy trade-offs in rapid-aimed movements. It highlights the numerous mathematical and theoretical interpretations that have been proposed in recent decades. Although the variety of points of view reflects the richness of the field and the high degree of interest that such basic phenomena attract in the understanding of human movements, it calls into question the ability of 'many models to explain the basic observations consistently reported in the field. This target article summarizes the kinematic theory of rapid human movements, proposed recently by R. Plamondon (1993b; 1993c; 1995a; 1995b), and analyzes its predictions in the context of speed/accuracy trade-offs. Data from human movement literature are reanalyzed and reinterpreted in the context of the new theory. It is shown that the various aspects of speed/accuracy trade-offs can be taken into account by considering the asymptotic behavior of a large number of coupled linear systems, from which a delta-lognormal law can be derived to describe the velocity profile of an end-effector driven by a neuromuscular synergy. This law not only describes velocity profiles almost perfectly, it also predicts the kinematic properties of simple rapid movements and provides a consistent framework for the analysis of different types of speed/accuracy trade-offs using a quadratic (or power) law that emerges from the model.

A neural model for generating and learning a rapid movement sequence.

In this article, a neural model for generating and learning a rapid ballistic movement sequence in two-dimensional (2D) space is presented and evaluated in the light of some considerations about handwriting generation. The model is based on a central nucleus (called a planning space) consisting of a fully connected grid of leaky integrators simulating neurons, and reading an input vector [symbol: see text] (t) which represents the external movement of the end effector. The movement sequencing results in a succession of motor strokes whose instantiation is controlled by the global activation of the planning space as defined by a competitive interaction between the neurons of the grid. Constraints such as spatial accuracy and movement time are exploited for the correct synchronization of the impulse commands. These commands are then fed into a neuromuscular synergy whose output is governed by a delta lognormal equation. Each movement sequence is memorized originally as a symbolic engram representing the sequence of the principal reference points of the 2D movement. These points, called virtual targets, correspond to the targets of each single rapid motor stroke composing the movement sequence. The task during the learning phase is to detect the engram corresponding to a new observed movement; the process is controlled by the dynamics of the neural grid.

A kinematic theory of rapid human movements. Part I. Movement representation and generation.

This paper proposes a kinematic theory that can be used to study and analyze rapid human movements. It describes a synergy in terms of the agonist and antagonist neuromuscular systems involved in the production of these movements. It is shown that these systems have a log-normal impulse response that results from the limiting behavior of a large number of interdependent neuromuscular networks, as predicted by the central limit theorem. The delta log-normal law that follows from this model is very general and can reproduce almost perfectly the complete velocity patterns of an end-effector. The theory accounts for the invariance and rescalability of these patterns, as well as for the various observations that have been reported concerning the change in maximum and mean velocities, time to maximum velocity, etc., under different experimental conditions. Movement time, load effects, and control strategies are discussed in a companion paper.

A kinematic theory of rapid human movements. Part II. Movement time and control.

This paper describes how a synergy made up of a pair of agonist and antagonist systems involved in the production of a rapid movement can control movement time. A quadratic law is derived to predict the movement time as a function of the various parameters describing the neuromuscular synergy. Conditions for a simplified description of the process, using a power law, are also presented. It is predicted that movement time can be controlled at the input level by the ratio of the agonist to antagonist commands or at the system level by modifying the total log-time delay or the log-response time of the agonist or antagonist neuromuscular networks. Adapting this approach to the specific case of movements executed under different spatial accuracy demands, it is found that movement time is linked to the inverse of the relative spatial error by similar laws. The whole approach is used to explain within a single framework all the observations that have been reported concerning speed/accuracy trade-offs. Strategies for controlling movement amplitude and duration are analyzed, and other predictions dealing with EMG, acceleration patterns, load effects and changes in the asymmetry of the velocity profile are also discussed.

Mainstreaming chiropractic: tracing the American Chiropractic Association.

The American Chiropractic Association (ACA) as it is known today was formed by a series of amalgamations. Starting with the Universal Chiropractic Association (UCA) of 1906 and the original American Chiropractic Association (ACA) of 1922, the two associations merged to form the National Chiropractic Association (NCA) in 1930. This Association merged with the New American Chiropractic Association (ACA) formed by non-NCA Association members and a splinter group from the International Chiropractors Association (ICA) in 1963. The total merger including all of NCA's assets, facilities, resources, personnel and membership was completed by 1964.

Looking at handwriting generation from a velocity control perspective.

This paper presents a model that explains the origin of the asymmetric bell-shaped velocity profiles generally observed in handwriting and other rapid movements. Applying the central limit theorem to describe the converging behavior of a sequence of dependent neural and muscular networks, it is shown that velocity profiles can be described by log-normal curves. An analysis-by-synthesis experiment is reported to support the model and to specify its mathematical implementation. Practical implications of this approach are discussed at the end of the paper to provide an analytical definition of a stroke, to clarify the concept of fluency and to suggest a powerful method for segmenting complex movements, particularly cursive script.

Modelling velocity profiles of rapid movements: a comparative study.

In this paper we compare 23 different models that can be used to describe the asymmetric bell-shaped velocity profiles of rapid-aimed movements. The comparison is performed with the help of an analysis-by-synthesis experiment over a database of 1052 straight lines produced by nine human subjects. For each line and for each model, a set of parameters is extracted that minimizes the error between the original and the reconstructed data. Performance analysis on the basis of the mean-square-error clearly reflects the superiority of the support-bounded lognormal model to globally describe the velocity profile characterizing rapid movements.