Evaluation of Speaker Normalization Methods for Vowel Recognition Using Fuzzy ARTMAP and K-NN

A procedure that uses fuzzy ARTMAP and K-Nearest Neighbor (K-NN) categorizers to evaluate intrinsic and extrinsic speaker normalization methods is described. Each classifier is trained on preprocessed, or normalized, vowel tokens from about 30% of the speakers of the Peterson-Barney database, then tested on data from the remaining speakers. Intrinsic normalization methods included one nonscaled, four psychophysical scales (bark, bark with end-correction, mel, ERB), and three log scales, each tested on four different combinations of the fundamental (Fo) and the formants (F1 , F2, F3). For each scale and frequency combination, four extrinsic speaker adaptation schemes were tested: centroid subtraction across all frequencies (CS), centroid subtraction for each frequency (CSi), linear scale (LS), and linear transformation (LT). A total of 32 intrinsic and 128 extrinsic methods were thus compared. Fuzzy ARTMAP and K-NN showed similar trends, with K-NN performing somewhat better and fuzzy ARTMAP requiring about 1/10 as much memory. The optimal intrinsic normalization method was bark scale, or bark with end-correction, using the differences between all frequencies (Diff All). The order of performance for the extrinsic methods was LT, CSi, LS, and CS, with fuzzy AHTMAP performing best using bark scale with Diff All; and K-NN choosing psychophysical measures for all except CSi.

Fuzzy ARTMAP, Slow Learning and Probability Estimation

A nonparametric probability estimation procedure using the fuzzy ARTMAP neural network is here described. Because the procedure does not make a priori assumptions about underlying probability distributions, it yields accurate estimates on a wide variety of prediction tasks. Fuzzy ARTMAP is used to perform probability estimation in two different modes. In a 'slow-learning' mode, input-output associations change slowly, with the strength of each association computing a conditional probability estimate. In 'max-nodes' mode, a fixed number of categories are coded during an initial fast learning interval, and weights are then tuned by slow learning. Simulations illustrate system performance on tasks in which various numbers of clusters in the set of input vectors mapped to a given class.

ART-EMAP: A Neural Network Architecture for Learning and Prediction by Evidence Accumulation

This paper introduces ART-EMAP, a neural architecture that uses spatial and temporal evidence accumulation to extend the capabilities of fuzzy ARTMAP. ART-EMAP combines supervised and unsupervised learning and a medium-term memory process to accomplish stable pattern category recognition in a noisy input environment. The ART-EMAP system features (i) distributed pattern registration at a view category field; (ii) a decision criterion for mapping between view and object categories which can delay categorization of ambiguous objects and trigger an evidence accumulation process when faced with a low confidence prediction; (iii) a process that accumulates evidence at a medium-term memory (MTM) field; and (iv) an unsupervised learning algorithm to fine-tune performance after a limited initial period of supervised network training. ART-EMAP dynamics are illustrated with a benchmark simulation example. Applications include 3-D object recognition from a series of ambiguous 2-D views.

Rule Extraction, Fuzzy ARTMAP, and Medical Databases

This paper shows how knowledge, in the form of fuzzy rules, can be derived from a self-organizing supervised learning neural network called fuzzy ARTMAP. Rule extraction proceeds in two stages: pruning removes those recognition nodes whose confidence index falls below a selected threshold; and quantization of continuous learned weights allows the final system state to be translated into a usable set of rules. Simulations on a medical prediction problem, the Pima Indian Diabetes (PID) database, illustrate the method. In the simulations, pruned networks about 1/3 the size of the original actually show improved performance. Quantization yields comprehensible rules with only slight degradation in test set prediction performance.

Brightness Perception, Illusory Contours and Corticogeniculate Feedback

A neural network model of early visual processing offers an explanation of brightness effects often associated with illusory contours. Top-down feedback from the model's analog of visual cortical complex cells to model lateral geniculate nucleus (LGN) cells are used to enhance contrast at line ends and other areas of boundary discontinuity. The result is an increase in perceived brightness outside a dark line end, akin to what Kennedy (1979) termed "brightness buttons" in his analysis of visual illusions. When several lines form a suitable configuration, as in an Ehrenstein pattern, the perceptual effect of enhanced brightness can be quite strong. Model simulations show the generation of brightness buttons. With the LGN model circuitry embedded in a larger model of preattentive vision, simulations using complex inputs show the interaction of the brightness buttons with real and illusory contours.

Statistical Properties of Single and Competing Non-Linear Fast-Slow Oscillators in Noise

Statistical properties offast-slow Ellias-Grossberg oscillators are studied in response to deterministic and noisy inputs. Oscillatory responses remain stable in noise due to the slow inhibitory variable, which establishes an adaptation level that centers the oscillatory responses of the fast excitatory variable to deterministic and noisy inputs. Competitive interactions between oscillators improve the stability in noise. Although individual oscillation amplitudes decrease with input amplitude, the average to'tal activity increases with input amplitude, thereby suggesting that oscillator output is evaluated by a slow process at downstream network sites.

A Neural Theory of Visual Search: Recursive Attention to Segmentations and Surfaces

A neural theory is proposed in which visual search is accomplished by perceptual grouping and segregation, which occurs simultaneous across the visual field, and object recognition, which is restricted to a selected region of the field. The theory offers an alternative hypothesis to recently developed variations on Feature Integration Theory (Treisman, and Sato, 1991) and Guided Search Model (Wolfe, Cave, and Franzel, 1989). A neural architecture and search algorithm is specified that quantitatively explains a wide range of psychophysical search data (Wolfe, Cave, and Franzel, 1989; Cohen, and lvry, 1991; Mordkoff, Yantis, and Egeth, 1990; Treisman, and Sato, 1991).

Processing of Synthetic Aperture Radar Images by a Multiscale Boundary Contour System and Feature Contour System

An improved Boundary Contour System (BCS) and Feature Contour System (FCS) neural network model of preattentive vision is applied to large images containing range data gathered by a synthetic aperture radar (SAR) sensor. The goal of processing is to make structures such as motor vehicles, roads, or buildings more salient and more interpretable to human observers than they are in the original imagery. Early processing by shunting center-surround networks compresses signal dynamic range and performs local contrast enhancement. Subsequent processing by filters sensitive to oriented contrast, including short-range competition and long-range cooperation, segments the image into regions. The segmentation is performed by three "copies" of the BCS and FCS, of small, medium, and large scales, wherein the "short-range" and "long-range" interactions within each scale occur over smaller or larger distances, corresponding to the size of the early filters of each scale. A diffusive filling-in operation within the segmented regions at each scale produces coherent surface representations. The combination of BCS and FCS helps to locate and enhance structure over regions of many pixels, without the resulting blur characteristic of approaches based on low spatial frequency filtering alone.

Orientational Harmonic Model for Rotation, Translation, and Scale Invariant Pattern Representation in Biological Vision

An extension to the orientational harmonic model is presented as a rotation, translation, and scale invariant representation of geometrical form in biological vision.

Orientational Harmonic Model for Rotation, Translation, and Scale Invariant Pattern Representation in Biological Vision

The proposed model, called the combinatorial and competitive spatio-temporal memory or CCSTM, provides an elegant solution to the general problem of having to store and recall spatio-temporal patterns in which states or sequences of states can recur in various contexts. For example, fig. 1 shows two state sequences that have a common subsequence, C and D. The CCSTM assumes that any state has a distributed representation as a collection of features. Each feature has an associated competitive module (CM) containing K cells. On any given occurrence of a particular feature, A, exactly one of the cells in CMA will be chosen to represent it. It is the particular set of cells active on the previous time step that determines which cells are chosen to represent instances of their associated features on the current time step. If we assume that typically S features are active in any state then any state has K^S different neural representations. This huge space of possible neural representations of any state is what underlies the model's ability to store and recall numerous context-sensitive state sequences. The purpose of this paper is simply to describe this mechanism.

A Memory Model for Concept Hierarchy Representation and Commonsense Reasoning

Most associative memory models perform one level mapping between predefined sets of input and output patterns1 and are unable to represent hierarchical knowledge. Complex AI systems allow hierarchical representation of concepts, but generally do not have learning capabilities. In this paper, a memory model is proposed which forms concept hierarchy by learning sample relations between concepts. All concepts are represented in a concept layer. Relations between a concept and its defining lower level concepts, are chunked as cognitive codes represented in a coding layer. By updating memory contents in the concept layer through code firing in the coding layer, the system is able to perform an important class of commonsense reasoning, namely recognition and inheritance.

A Neural Theory of Attentive Visual Search: Interactions of Boundary, Surface, Spatial, and Object Representations

Visual search data are given a unified quantitative explanation by a model of how spatial maps in the parietal cortex and object recognition categories in the inferotemporal cortex deploy attentional resources as they reciprocally interact with visual representations in the prestriate cortex. The model visual representations arc organized into multiple boundary and surface representations. Visual search in the model is initiated by organizing multiple items that lie within a given boundary or surface representation into a candidate search grouping. These items arc compared with object recognition categories to test for matches or mismatches. Mismatches can trigger deeper searches and recursive selection of new groupings until a target object io identified. This search model is algorithmically specified to quantitatively simulate search data using a single set of parameters, as well as to qualitatively explain a still larger data base, including data of Aks and Enns (1992), Bravo and Blake (1990), Chellazzi, Miller, Duncan, and Desimone (1993), Egeth, Viri, and Garbart (1984), Cohen and Ivry (1991), Enno and Rensink (1990), He and Nakayarna (1992), Humphreys, Quinlan, and Riddoch (1989), Mordkoff, Yantis, and Egeth (1990), Nakayama and Silverman (1986), Treisman and Gelade (1980), Treisman and Sato (1990), Wolfe, Cave, and Franzel (1989), and Wolfe and Friedman-Hill (1992). The model hereby provides an alternative to recent variations on the Feature Integration and Guided Search models, and grounds the analysis of visual search in neural models of preattentive vision, attentive object learning and categorization, and attentive spatial localization and orientation.

Speaker Normalization Methods for Vowel Cognition: Comparative Analysis Using Neural Network and Nearest Neighbor Classifiers

Intrinsic and extrinsic speaker normalization methods are systematically compared using a neural network (fuzzy ARTMAP) and L1 and L2 K-Nearest Neighbor (K-NN) categorizers trained and tested on disjoint sets of speakers of the Peterson-Barney vowel database. Intrinsic methods include one nonscaled, four psychophysical scales (bark, bark with endcorrection, mel, ERB), and three log scales, each tested on four combinations of F0 , F1, F2, F3. Extrinsic methods include four speaker adaptation schemes, each combined with the 32 intrinsic methods: centroid subtraction across all frequencies (CS), centroid subtraction for each frequency (CSi), linear scale (LS), and linear transformation (LT). ARTMAP and KNN show similar trends, with K-NN performing better, but requiring about ten times as much memory. The optimal intrinsic normalization method is bark scale, or bark with endcorrection, using the differences between all frequencies (Diff All). The order of performance for the extrinsic methods is LT, CSi, LS, and CS, with fuzzy ARTMAP performing best using bark scale with Diff All; and K-NN choosing psychophysical measures for all except CSi.

Extracted Memory from Temporal Patterns Using Adaptive Resonance and Recurrent Network

We can recognize objects through receiving continuously huge temporal information including redundancy and noise, and can memorize them. This paper proposes a neural network model which extracts pre-recognized patterns from temporally sequential patterns which include redundancy, and memorizes the patterns temporarily. This model consists of an adaptive resonance system and a recurrent time-delay network. The extraction is executed by the matching mechanism of the adaptive resonance system, and the temporal information is processed and stored by the recurrent network. Simple simulations are examined to exemplify the property of extraction.

The What-And-Where Filter: A Spatial Mapping Neural Network for Object Recognition and Image Understanding

The What-and-Where filter forms part of a neural network architecture for spatial mapping, object recognition, and image understanding. The Where fllter responds to an image figure that has been separated from its background. It generates a spatial map whose cell activations simultaneously represent the position, orientation, ancl size of all tbe figures in a scene (where they are). This spatial map may he used to direct spatially localized attention to these image features. A multiscale array of oriented detectors, followed by competitve and interpolative interactions between position, orientation, and size scales, is used to define the Where filter. This analysis discloses several issues that need to be dealt with by a spatial mapping system that is based upon oriented filters, such as the role of cliff filters with and without normalization, the double peak problem of maximum orientation across size scale, and the different self-similar interpolation properties across orientation than across size scale. Several computationally efficient Where filters are proposed. The Where filter rnay be used for parallel transformation of multiple image figures into invariant representations that are insensitive to the figures' original position, orientation, and size. These invariant figural representations form part of a system devoted to attentive object learning and recognition (what it is). Unlike some alternative models where serial search for a target occurs, a What and Where representation can he used to rapidly search in parallel for a desired target in a scene. Such a representation can also be used to learn multidimensional representations of objects and their spatial relationships for purposes of image understanding. The What-and-Where filter is inspired by neurobiological data showing that a Where processing stream in the cerebral cortex is used for attentive spatial localization and orientation, whereas a What processing stream is used for attentive object learning and recognition.