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 study on multilingual deep neural network (DNN) based acoustic modeling and its application to new languages. We investigate the effect of phone merging on multilingual DNN in context of rapid language adaptation. Moreover, the combination of multilingual DNNs with Kullback-Leibler divergence based acoustic modeling (KL-HMM) is explored. Using ten different languages from the...
Recently, it has been demonstrated that Commercial Microwave Networks (CMN) can be considered as an opportunistic sensor networks for rainfall monitoring, and in particular, for rain fields reconstruction. While different rainfall mapping techniques have been proposed, their absolute performance has never been evaluated. This paper presents a novel algorithm, which generates an accurate reconstruction...
Compressed Sensing (CS) has been recently applied to direction of arrival (DOA) estimation, leveraging the fact that a superposition of planar wavefronts corresponds to a sparse angular power spectrum. However, to apply the CS framework we need to construct a finite dictionary by sampling the angular domain with a predefined sampling grid. Therefore, the target locations are almost surely not located...
We introduce a reconstruction formula that allows one to recover an N-order tensor X ∊ RI1×…×In from a reduced set of multi-way compressive measurements by exploiting its low multilinear rank structure. It is proved that, in the matrix case (N = 2), the proposed reconstruction is stable in the sense that the approximation error is proportional to the one provided by the best low-rank approximation,...
In this article we present an angle of arrival (AoA) multi-robot system for rescue purposes which takes advantage of robots' mobility to improve the position estimate of an unknown target. The robots move according to a certain trajectory (a sequence of stopping points) designed to minimize the variance of the AoA estimation. We present two different techniques to generate these optimal trajectories,...
Compressed Sensing (CS) provides a rich mathematical framework to efficiently acquire a sparse signal from few non-adaptive measurements. In radar imaging, most scenes are sparse and CS can be successfully applied for efficiently acquiring the target scene. Although the use of CS in radar is advantageous in many aspects, a higher noise in the received signal makes the output of CS unreliable. We propose...
Based on affine projection algorithm (APA) in adaptive filtering and the technique of parallel computing, we propose a novel algorithm called ℓ0-APA with its parallel implementation for sparse system identification and sparse signal recovery. For sparse system identification, parallel ℓ0-APA can serve as an effective approach for practical hardware implementation, since it lowers the requirement on...
Non-negative matrix factorization (NMF) is a popular method for learning interpretable features from non-negative data, such as counts or magnitudes. Different cost functions are used with NMF in different applications. We develop an algorithm, based on the alternating direction method of multipliers, that tackles NMF problems whose cost function is a beta-divergence, a broad class of divergence functions...
This paper considers the ergodic block fading multi-user Gaussian interference channel (IC) in which each source desires to communicate to an intended destination. We assume that there is no CSI a priori available at terminals. We develop achievable rate results and compute the associated degrees of freedom by using a pilot-assisted interference alignment scheme. In this scheme, each source first...
A mixed radix algorithm for the in-place fast Fourier transform (FFT), which is broadly used in most embedded signal processing fields, can be explicitly expressed by an iterative equation based on the Cooley-Tukey algorithm. The expression can be applied to either decimation-in-time (DIT) or decimation-in-frequency (DIF) FFTs with ordered inputs. For many newly emerging low power portable computing...
We introduce a two-stage cascaded scheme to rescore Confusion Networks (CNs) for Keyword Search in the context of Low-Resource Languages. In the first stage we rescore the CN to improve the error rate of the 1-best hypothesis using a large number of lexical, phonetic, false alarms and structural features. Using a rank learning Support Vector Machine classifier, we obtain WER gains between 0.54% and...
Though sparse features have produced significant gains over traditional dense features in statistical machine translation, careful feature selection and feature engineering are necessary to avoid over-fitting in optimizations. However, many sparse features are highly overlapping with each other; that is, they cover the same or similar information of translational equivalence from slightly different...
Dimensionality reduction plays an important role in machine learning techniques. In classification, data transformation aims to reduce the number of feature dimensions, whereas attempts to enhance the class separability. To this end, we propose a new classifier-independent criterion called “Sum-of-Signal-to-Noise-Ratio” (SoSNR). A framework designed for maximization with respect to this criterion...
In this paper we propose a non-negative matrix factorization (NMF) model with piecewise-constant activation coefficients. This structure is enforced using a total variation penalty on the rows of the activation matrix. The resulting optimization problem is solved with a majorization-minimization procedure. The proposed algorithm is well suited to analyze data explained by underlying piecewise-constant...
Exposed-datapath architectures yield small, low-power processors that trade instruction word length for aggressive compile-time scheduling and a high degree of instruction-level parallelism. In this paper, we present a general-purpose parallel accelerator consisting of a main processor and eight symmetric clusters, all in a single core. Use of a lightweight and memory-efficient application programming...
Current mobile devices are unable to execute complex vision applications in a timely and power efficient manner without offloading some of the computation. This paper examines the tradeoffs that arise from executing some of the workload onboard and some remotely. Feature extraction and matching play an essential role in image classification and have the potential to be executed locally. Along with...
Unsupervised feature learning with deep networks has been widely studied in the recent years. Despite the progress, most existing models would be fragile to non-Gaussian noises and outliers due to the criterion of mean square error (MSE). In this paper, we propose a robust stacked autoencoder (R-SAE) based on maximum correntropy criterion (MCC) to deal with the data containing non-Gaussian noises...
Combating the intersymbol interference is an important issue in single-carrier block transmission systems. In this paper, we present a nonlinear equalizer that combines frequency-domain (FD) pre-filtering with time-domain tree search detection. Simulation results show that the proposed algorithm achieves a detection performance that is very close to that of the conventional tree search equalizer (which...
This paper presents a study for the estimation of 2-D maps of atmospheric water vapour content from integrated water vapour measurements carried out by a constellation of co-rotating low earth orbit satellites. The proposed method uses the normalised differential spectral attenuation (NDSA) approach — able to achieve integrated water vapour content information from attenuation measurements over microwave...
An implicit premise in using an acoustic echo canceller (AEC) is that the clock for A/D conversion for a microphone and the clock for D/A conversion for a loudspeaker work synchronously. Even a slight difference in sampling rate between the clocks critically degrades the echo cancelling performance. This paper describes a method of making an AEC in the frequency domain that can handle a mismatch in...
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.