The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
This paper presents a novel application of convolutional neural networks (CNNs) for the task of acoustic scene classification (ASC). We here propose the use of a CNN trained to classify short sequences of audio, represented by their log-mel spectrogram. We also introduce a training method that can be used under particular circumstances in order to make full use of small datasets. The proposed system...
Affective computing, particularly emotion and personality trait recognition, is of increasing interest in many research disciplines. The interplay of emotion and personality shows itself in the first impression left on other people. Moreover, the ambient information, e.g. the environment and objects surrounding the subject, also affect these impressions. In this work, we employ pre-trained Deep Convolutional...
Side-scan sonar technology has been used over the last three decades for underwater surveying and imaging. Application areas of side-scan sonar include archaeology, security and defence, seabed classification, and environmental surveying. In recent years the use of autonomous underwater systems has allowed for automatic collection of data. Along with automatic collection of data comes the need to...
Kernel density model works well for limited training data in acoustic modeling. In this paper, we improve the kernel density-based acoustic model for low resource language speech recognition. In our previous study, we demonstrated the effectiveness of the kernel density-based acoustic model on discriminative features such as cross-lingual bottleneck features. In this paper, we propose to learn a Mahalanobis-based...
In this paper, we investigate the use of the proposed non-parametric exemplar-based acoustic modeling for the NIST Open Keyword Search 2015 Evaluation. Specifically, kernel-density model is used to replace GMM in HMM/GMM (Hidden Markov Model / Gaussian Mixture Model) or DNN in HMM/DNN (Hidden Markov Model / Deep Neural Network) acoustic model to predict the emission probability of HMM states. To get...
Underwater target classification is a very demanding task owing to ever changing complicated nature of the underwater communication channels. Underwater target classification system identifies targets from a mixture of underwater events by its characteristic signature. The characteristic signatures pertaining to each target are patterned by feature recognition algorithms operating on hydrophone captured...
Effective representation plays an important role in automatic spoken language identification (LID). Recently, several representations that employ a pre-trained deep neural network (DNN) as the front-end feature extractor, have achieved state-of-the-art performance. However the performance is still far from satisfactory for dialect and short-duration utterance identification tasks, due to the deficiency...
The control of an acoustic echo canceller (AEC) is an essential part of hands-free telephone sets. Due to the fact that no single estimator is yet known to reliably control the AEC, various estimators should be implemented. Nevertheless, the combination of several estimators is quite difficult and usually determined heuristically. In this paper, an approach for automatic combination of estimators,...
The identification and classification of noise sources in the ocean has become a key task of modern underwater acoustic signal processing and because of the ever changing and complicated oceanic environment, underwater target classification has become a demanding task. An underwater acoustic target classification system identifies the acoustic target from the characteristic acoustic signature. The...
Production of railway axles (i.e., one of the basic material of the modern train) is an elaborate process unfree from faults and problems. Errors during the manufacturing or the plies' overlapping, in fact, can cause particular flaws in the resulting material, so compromising its same integrity. Within this framework, ultrasonic tests could be useful to characterize the presence of defect, depending...
In this paper, we propose a discriminative method for the acoustic feature based language recognizer, which is a modification of the polynomial expansion in generalized linear discriminant sequence (GLDS) kernel. It is inspired by the Gaussian mixture model-support vector machine (GMM-SVM) system which has been successfully used in both speaker and language recognition. Because of the restriction...
In this paper, we propose a kernel multi-metric learning algorithm for multi-channel transient acoustic signal classification. The proposed method learns a set of metrics jointly for multi-channel transient acoustic signals in a kernel-induced feature space to exploit the non-linearity of the data for improving the classification performance. An effective algorithm is developed for the task of learning...
Currently, most of the acoustic model selection work is done empirically or heuristically or even arbitrarily. In this paper, Genetic Algorithm (GA) based and Particle Swarm Optimization (PSO) based algorithms that consider the number of states and the kernel numbers for the states simultaneously and reject the uniform allocation of Gaussian kernels are proposed to automatically optimize acoustic...
Recently, we introduced a method to recover the controlling parameters of linear systems using diffusion kernels. In this paper, we apply our approach to the problem of source localization in a reverberant room using measurements from a single microphone. Prior recordings of signals from various known locations in the room are required for training and calibration. The proposed algorithm relies on...
In this paper, we present a novel joint sparse representation based method for acoustic signal classification with multiple measurements. The proposed method exploits the correlations among the multiple measurements with the notion of joint sparsity for improving the classification accuracy. Extensive experiments are carried out on real acoustic data sets and the results are compared with the conventional...
We describe a new approach for phoneme recognition which aims at minimizing the phoneme error rate. Building on structured prediction techniques, we formulate the phoneme recognizer as a linear combination of feature functions. We state a PAC-Bayesian generalization bound, which gives an upper-bound on the expected phoneme error rate in terms of the empirical phoneme error rate. Our algorithm is derived...
This paper introduces a discriminative extension to whole-word point process modeling techniques. Meant to circumvent the strong independence assumptions of their generative predecessors, discriminative point process models (DPPM) are trained to distinguish the composite temporal patterns of phonetic events produced for a given word from those of its impostors. Using correct and incorrect word hypotheses...
Neural networks are a useful alternative to Gaussian mixture models for acoustic modeling; however, training multilayer networks involves a difficult, nonconvex optimization that requires some “art” to make work well in practice. In this paper we investigate the use of arccosine kernels for speech recognition, using these kernels in a hybrid support vector machine/hidden Markov model recognition system...
In this paper, the issue of composite defects diagnosis by applying the support vector machine (SVM) was addressed. The component analysis was performed initially to extract the features and to reduce the dimensionality of original data features. Kernel parameters selection of support vector machine which has great influence on the performance of defects classification has been discussed in this work...
Using discriminative classifiers, such as Support Vector Machines (SVMs) in combination with, or as an alternative to, Hidden Markov Models (HMMs) has a number of advantages for difficult speech recognition tasks. For example, the models can make use of additional dependencies in the observation sequences than HMMs provided the appropriate form of kernel is used. However standard SVMs are binary classifiers,...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.