Efrén González

Foucault test: shadowgram modeling from the physical theory for quantitative evaluations

The physical theory of the Foucault test has been investigated to represent the complex amplitude and irradiance of the shadowgram in terms of the wavefront error; however, most of the studies have limited the treatment for the particular case of nearly diffraction-limited optical devices (i.e., aberrations smaller than the wavelength). In this paper we discard this restriction, and in order to show a more precise interpretation from the physical theory we derive expressions for the complex amplitude and the irradiance over an optical device with larger aberrations. To the best of our knowledge, it is the first time an expression is obtained in closed form. As will be seen, the result of this derivation is obtained using some properties of the Hilbert transform that permit representing the irradiance in a simple form in terms of the partial derivatives of the wavefront error. Additionally, we briefly describe from this point of view a methodology for the quantitative analysis of the test.

Semi-Huber potential function for image segmentation

In this work, a novel model of Markov Random Field (MRF) is introduced. Such a model is based on a proposed Semi-Huber potential function and it is applied successfully to image segmentation in presence of noise. The main difference with respect to other half-quadratic models that have been taken as a reference is, that the number of parameters to be tuned in the proposed model is smaller and simpler. The idea is then, to choose adequate parameter values heuristically for a good segmentation of the image. In that sense, some experimental results show that the proposed model allows an easier parameter adjustment with reasonable computation times.

A tour of nonlocal means techniques for image filtering

The present work proposes a review and comparison of different Nonlocal Means (NLM) methods in the task of digital image filtering. Some different alternatives to change the classical exponential kernel function used in NLM methods are explored. Moreover, some approaches that change the geometry of the neighborhood and use dimensionality reduction of the neighborhood or patches onto principal component analysis (PCA) are also analyzed, and their performance is compared with respect to the classic NLM method. Mainly, six approaches were compared using quantitative and qualitative evaluations, to do this an homogenous framework has been established using the same simulation platform, the same computer, and same conditions for the initializing parameters. One will notice that particularly, the BM3D SAPCA approach gives the best denoising results, but in contrast, the computation times of this method were the longest.

A case study of speech recognition in Spanish: From conventional to deep approach

The aim of this paper is to exhibit a comparative case study of the conventional speech recognition GMM-HMM (Gaussian mixture model — hidden Markov model) architecture and the recent model based on deep neural networks. During years the GMM approach has controlled the speech recognition tasks, however it has been surpassed with the resurgence of artificial neural networks. To exemplify these acoustic modeling frameworks, a case study has been conducted by using the Kaldi toolkit, employing a personalized speaker-independent mid-vocabulary voice corpus for recognition of digit strings and personal name lists in latin spanish on a connected-words phone dialing task. The speech recognition accuracy obtained in the results shows a better word error rate by using the DNN acoustic modeling. A 20.71% relative improvement is obtained with DNN-HMM models (3.33% WER) in respect to the lowest GMM-HMM rate (4.20% WER).

Speech recognition in a dialog system: from conventional to deep processing: A case study applied to Spanish

The aim of this paper is to illustrate an overview of the automatic speech recognition (ASR) module in a spoken dialog system and how it has evolved from the conventional GMM-HMM (Gaussian mixture model - hidden Markov model) architecture toward the recent nonlinear DNN-HMM (deep neural network) scheme. GMMs have dominated for a long time the baseline of speech recognition, but in the past years with the resurgence of artificial neural networks (ANNs), the former models have been surpassed in most recognition tasks. An outstanding consideration for ANNs-based acoustic model is the fact that their weights can be adjusted in two training steps: i) initialization of the weights (with or without pre-training) and ii) fine-tuning. To exemplify these frameworks, a case study is realized by using the Kaldi toolkit, employing a mid-vocabulary with a personalized speaker-independent voice corpus on a connected-words phone dialing environment operated for recognition of digit strings and personal name lists in Spanish from Mexico. The obtained results show a reasonable accuracy in the speech recognition performance through the DNN acoustic modeling. A word error rate (WER) of 1.49% for context-dependent DNN-HMM is achieved, providing a 30% relative improvement with regard to the best GMM-HMM result in these experiments (2.12% WER).

Training deep neural networks with non-uniform frame-level cost function for automatic speech recognition

The aim of this paper is to exhibit two new variations of the frame-level cost function for training a deep neural network in order to achieve better word error rates in speech recognition. Optimization methods and their minimization functions are underlying aspects to consider when someone is working on neural nets, and hence their improvement is one of the salient objectives of researchers, and this paper deals in part with such a situation. The first proposed framework is based on the concept of extropy, the complementary dual function of an uncertainty measure. The conventional cross-entropy function can be mapped to a non-uniform loss function based on its corresponding extropy, enhancing the frames that have ambiguity in their belonging to specific senones. The second proposal makes a fusion of the presented mapped cross-entropy function and the idea of boosted cross-entropy, which emphasizes those frames with low target posterior probability. The proposed approaches have been performed by using a personalized mid-vocabulary speaker-independent voice corpus. This dataset is employed for recognition of digit strings and personal name lists in Spanish from the northern central part of Mexico on a connected-words phone dialing task. A relative word error rate improvement of 12.3%

Regularized quadratic cost-function for integrating wave-front gradient fields

12.3\%

Foucault test: a quantitative evaluation method

and 10.7%

Hilbert vs. exponential Kernel functionals for Nonlocal Means image filtering

10.7\%

Demodulation of single interferograms using a sliding 2-D continuous wavelet transform method

is obtained with the two proposed approaches, respectively, with regard to the conventional well-established cross-entropy objective function.