Raffaele Parisi

Car plate recognition by neural networks and image processing

In this paper we describe an experimental system for the recognition of Italian-style car license plates. Images are usually taken from a camera at a toll gate and preprocessed by a fast and robust 1-D DFT scheme to find the plate and character positions. Characters are classified by a multilayer neural network trained by the recently developed BRLS learning algorithm. The same neural network replaces both the traditional feature extractor and the classifier. The percentage of correctly recognized characters reaches the best scores obtained in literature, being highly insensitive to the environment variability, while the architecture appears best suited for parallel implementation on programmable DSP processors.

A generalized learning paradigm exploiting the structure of feedforward neural networks

In this paper a general class of fast learning algorithms for feedforward neural networks is introduced and described. The approach exploits the separability of each layer into linear and nonlinear blocks and consists of two steps. The first step is the descent of the error functional in the space of the outputs of the linear blocks (descent in the neuron space), which can be performed using any preferred optimization strategy. In the second step, each linear block is optimized separately by using a least squares (LS) criterion. To demonstrate the effectiveness of the new approach, a detailed treatment of a gradient descent in the neuron space is conducted. The main properties of this approach are the higher speed of convergence with respect to methods that employ an ordinary gradient descent in the weight space backpropagation (BP), better numerical conditioning, and lower computational cost compared to techniques based on the Hessian matrix. The numerical stability is assured by the use of robust LS linear system solvers, operating directly on the input data of each layer. Experimental results obtained in three problems are described, which confirm the effectiveness of the new method.

Fast adaptive digital equalization by recurrent neural networks

Neural networks (NNs) have been extensively applied to many signal processing problems. In particular, due to their capacity to form complex decision regions, NNs have been successfully used in adaptive equalization of digital communication channels. The mean square error (MSE) criterion, which is usually adopted in neural learning, is not directly related to the minimization of the classification error, i.e., bit error rate (BER), which is of interest in channel equalization. Moreover, common gradient-based learning techniques are often characterized by slow speed of convergence and numerical ill conditioning. In this paper, we introduce a novel approach to learning in recurrent neural networks (RNNs) that exploits the principle of discriminative learning, minimizing an error functional that is a direct measure of the classification error. The proposed method extends to RNNs a technique applied with success to fast learning of feedforward NNs and is based on the descent of the error functional in the space of the linear combinations of the neurons (the neuron space); its main features are higher speed of convergence and better numerical conditioning w.r.t. gradient-based approaches, whereas numerical stability is assured by the use of robust least squares solvers. Experiments regarding the equalization of PAM signals in different transmission channels are described, which demonstrate the effectiveness of the proposed approach.

Multi-source localization in reverberant environments by ROOT-MUSIC and clustering

Localization of acoustic sources in reverberant environments by microphone arrays remains a challenging task in audio signal processing. As a matter of fact, most assumptions of commonly adopted models are not met in real applications. Moreover, in practical systems it is not convenient or possible to employ sophisticated and costly architectures, that require precise synchronization and fast data shuffling among sensors. In this paper, a new robust multi-step procedure for speaker localization in reverberant rooms is introduced and described. The new approach is based on a disturbed harmonics model of time delays in the frequency domain and employs the well-known ROOT-MUSIC algorithm, after a preliminary distributed processing of the received signals. Candidate source positions are then estimated by clustering of raw TDOA estimates. Main features of the proposed approach, compared to previous solutions, are the capability of tracking multiple speakers and the high accuracy of the closed form TDOA estimator.

Source Localization in Reverberant Environments by Consistent Peak Selection

Acoustic source localization in the presence of reverberation is a difficult task. Conventional approaches, based on time delay estimation performed by generalized cross correlation (GCC) on a set of microphone pairs, followed by geometric triangulation, are often unsatisfactory. Prefiltering is usually adopted to reduce the spurious peaks due to reflections. In this work an alternative strategy is proposed, based on the concept that secondary peaks of the GCCs can be crucial in order to correctly locate the source. More specifically, an iterative weighting procedure is introduced, based on the rationale that peaks corresponding to the actual source position should be consistently weighted. The position estimate is then refined by use of an effective and fast clustering technique. Experimental results on simulated data demonstrate the effectiveness of the proposed solution.

Multi-Source Localization Strategies

Localization of multiple acoustic sources is an important task in many practical applications. However, in most cases adopted models are not fully adequate to describe real scenarios. In particular, in the presence of reverberation, the signal model should explicitly take into account both signals radiated by multiple sources and reflections. In alternative to Generalized Cross-Correlation methods, array processing concepts can be effectively applied to multi-source localization in reverberant environments. In this chapter, main features and limitations of wide-band array processing approaches are briefly reviewed. Furthermore, a new integrated localization and classification system, based on a robust frequency-domain Time Delay Of Arrival (TDOA) estimation followed by a spatial clustering of raw location estimates, is presented. The proposed method efficiently incorporates TDOA and array processing concepts in an unified approach. Results on simulated data are supplied.

Combined adaptive beamforming schemes for nonstationary interfering noise reduction

This paper introduces new adaptive beamforming methods for nonstationary noise reduction, designed to be robust against broadband interfering signals. In particular, we propose combined beamforming schemes within a standard adaptive beamforming system, such as the generalized sidelobe canceller (GSC). The novelty of such combined adaptive beamformers relies on the use of different adaptive sidelobe cancelling structures which allow the system to achieve robustness in nonstationary noisy environments. The combined structures are based on the convex combination of two multiple-input singleoutput (MISO) adaptive systems with complementary capabilities. The whole beamformer benefits from such combination and results to be able to preserve the best properties of each system. We introduce two different adaptive schemes, whose difference lies in the way of combining the MISO systems. Moreover, we present a further adaptive beamforming scheme which generalizes the previous techniques, thus improving the robustness against nonstationary interfering signals in multisource environments. The effectiveness of the proposed systems is also assessed in a nonstationary dense multipath environment. The experiments show that the proposed combined beamforming schemes are capable of enhancing the desired signal even in the presence of nonstationary interfering signals. & 2013 Elsevier B.V. All rights reserved.

An information theoretic approach to a novel nonlinear independent component analysis paradigm

This paper introduces a novel independent component analysis (ICA) approach to the separation of nonlinear convolutive mixtures. The proposed model is an extension of the well-known post nonlinear (PNL) mixing model and consists of the convolutive mixing of PNL mixtures. Theoretical proof of existence and uniqueness of the solution under proper assumptions is provided. Feedforward and recurrent demixing architectures based on spline neurons are introduced and compared. Source separation is performed by minimizing the mutual information of the output signals with respect to the network parameters. More specifically, the proposed architectures perform on-line nonlinear compensation and score function estimation by proper use of flexible spline nonlinearities, yielding a significant performance improvement in terms of source pdf matching and algorithm speed of convergence. Experimental tests on different signals are described to demonstrate the effectiveness of the proposed approach.

Cepstrum Prefiltering for Binaural Source Localization in Reverberant Environments

Binaural sound source localization can be performed by imitation of the fundamental mechanisms of the human auditory system, which is based on the integrated effects of ear, pinnae, head and torso. In particular, two physical cues can be exploited, i.e. the Interaural Time Difference (ITD) and the Interaural Level Difference (ILD). It is known that joint use of ITD and ILD provides good source azimuth estimations. In many practical situations binaural localization has to be performed in closed environments, where the presence of reverberation degrades the performance of available position estimators. In this paper a possible solution to this difficult problem is introduced. The proposed solution is based on proper use of cepstral prefiltering prior to source localization by ITD and ILD. It is shown that cepstrum can help in reducing the effects of reverberation, thus yielding better location estimates.

Comparison of Hammerstein and Wiener systems for nonlinear acoustic echo cancelers in reverberant environments

The aim of this paper is the presentation of a comparative analysis of Hammerstein and Wiener systems used for the problem of compensation of the nonlinear distortion due to non-ideality of amplifiers and loudspeakers in acoustic echo cancellation. The proposed solutions consist in a cascade of a flexible nonlinear function, whose shape can be modified during the learning process, and a linear adaptive filter in different order, respectively. Two different type of flexible nonlinearities are tested. Some numerical results show the effectiveness of the proposed approaches and underline that the Hammerstein system has better performances than the Wiener one.