Antonio M. Peinado

Co-authors

Following

Followers

Research Focus & Metrics

Explore full metrics on Scilit

Academic Career Length

36Years (1991-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications

18 April 2005 in IEEE Transactions on Speech and Audio Processing

Journal Article

Histogram equalization of speech representation for robust speech recognition

Ángel De La Torre

Antonio M. Peinado

Jose Segura

José Luis Pérez Córdoba

M.C. Benitez

A.J. Rubio

This paper describes a method of compensating for nonlinear distortions in speech representation caused by noise. The method described here is based on the histogram equalization method often used in digital image processing. Histogram equalization is applied to each component of the feature vector in order to improve the robustness of speech recognition systems. The paper describes how the proposed method can be applied to robust speech recognition and it is compared with other compensation techniques. The recognition experiments, including results in the AURORA II framework, demonstrate the effectiveness of histogram equalization when it is applied either alone or in combination with other compensation techniques.

19 September 2018 in IEEE Signal Processing Letters

Journal Article

A Deep Learning Loss Function Based on the Perceptual Evaluation of the Speech Quality

Juan Manuel Martín Doñas

Angel Manuel Gómez García

José Andrés González López

Antonio M. Peinado

This letter proposes a perceptual metric for speech quality evaluation, which is suitable, as a loss function, for training deep learning methods. This metric, derived from the perceptual evaluation of the speech quality algorithm, is computed in a per-frame basis and from the power spectra of the reference and processed speech signal. Thus, two disturbance terms, which account for distortion once auditory masking and threshold effects are factored in, amend the mean square error (MSE) loss function by introducing perceptual criteria based on human psychoacoustics. The proposed loss function is evaluated for noisy speech enhancement with deep neural networks. Experimental results show that our metric achieves significant gains in speech quality (evaluated using an objective metric and a listening test) when compared to using MSE or other perceptual-based loss functions from the literature.

1 January 1995 in IEEE Transactions on Signal Processing

Journal Article

Diagonalizing properties of the discrete cosine transforms

V. Sanchez

P. Garcia

Antonio M. Peinado

Jose Segura

A.J. Rubio

Since its introduction in 1974 by Ahmed et al., the discrete cosine transform (DCT) has become a significant tool in many areas of digital signal processing, especially in signal compression. There exist eight types of discrete cosine transforms (DCTs). We obtain the eight types of DCTs as the complete orthonormal set of eigenvectors generated by a general form of matrices in the same way as the discrete Fourier transform (DFT) can be obtained as the eigenvectors of an arbitrary circulant matrix. These matrices can be decomposed as the sum of a symmetric Toeplitz matrix plus a Hankel or close to Hankel matrix scaled by some constant factors. We also show that all the previously proposed generating matrices for the DCTs are simply particular cases of these general matrix forms. Using these matrices, we obtain, for each DCT, a class of stationary processes verifying certain conditions with respect to which the corresponding DCT has a good asymptotic behavior in the sense that it approaches Karhunen-Loeve transform performance as the block size N tends to infinity. As a particular result, we prove that the eight types of DCTs are asymptotically optimal for all finite-order Markov processes. We finally study the decorrelating power of the DCTs, obtaining expressions that show the decorrelating behavior of each DCT with respect to any stationary processes

4 August 2011 in Optics Express

Journal Article

Experimental demonstration of weak-light laser ranging and data communication for LISA

Juan Jose Esteban Delgado

Antonio F. García

Simon Barke

Antonio M. Peinado

Felipe Guzmán Cervantes

Karsten Danzmann

Interferometric gravitational wave detectors with an unequal and time-varying arm length configuration like the Laser Interferometer Space Antenna rely on time-delay interferometry (TDI) for laser frequency noise subtraction. However, the TDI algorithm requires a laser ranging scheme with meter accuracy over a five million kilometer arm length. At the end of each arm only about 100 pW of light power will be detected for gravitational wave measurements and only 1% of this power can be used for laser ranging in order to avoid degradation in the phase stability of the science measurements. Here, we present the first experimental demonstration of such a ranging scheme at 1 pW power levels using a Direct Sequence Spread Spectrum (DS/SS) modulation. This type of modulation also enables optical communication by encoding data with ranging signals and provides significant noise reduction against spurious interfering signals for bidirectional ranging. Experimental results show ranging measurements of 42 cm at 3 Hz and the viability of highly reliable data transfer at several kilobits per second.

28 July 2006

Book

Speech Recognition Over Digital Channels

Antonio M. Peinado

Jose Segura

Click on the title to browse this book

9 January 2013 in IEEE Transactions on Multimedia

Journal Article

Sequential Error Concealment for Video/Images by Sparse Linear Prediction

JØ

In this paper, we propose a novel sequential error concealment algorithm for video and images based on sparse linear prediction. Block-based coding schemes in packet loss environments are considered. Images are modelled by means of linear prediction, and missing macroblocks are sequentially reconstructed using the available groups of pixels. The optimal predictor coefficients are computed by applying a missing data regression imputation procedure with a sparsity constraint. Moreover, an efficient procedure for the computation of these coefficients based on an exponential approximation is also proposed. Both techniques provide high-quality reconstructions and outperform the state-of-the-art algorithms both in terms of PSNR and MS-SSIM.

About Me

Antonio M. Peinado (M'95–SM'05) received the M.S. and Ph.D. degrees in physics from the University of Granada, Spain, in 1987 and 1994, respectively. Since 1988, he has been with the University of Granada, where he has led several research projects related to signal processing and transmission. In 1989, he was a Consultant with the Speech Research Department, AT\&T Bell Labs, Murray Hill, NJ, USA, and, in 2018, a Visiting Scholar with the Language Technologies Institute of CMU, Pittsburgh, PA, USA. He has held the positions of an Associate Professor from 1996 to 2010 and a Full Professor since 2010 with the Department of Signal Theory, Networking and Communications, University of Granada, where he is currently the Head of the research group on Signal Processing, Multimedia Transmission and Speech/Audio Technologies. He authored numerous publications in international journals and conferences, and has co-authored the book entitled Speech Recognition Over Digital Channels (New York, NY, USA: Wiley, 2006). His current research interests are focused on several speech technologies (anti-spoofing for automatic speaker verification, speech enhancement, and robust speech recognition and transmission), image processing and proteomic signal processing. Prof. Peinado has been a reviewer for a number of international journals and conferences, an evaluator for project and grant proposals, and a Member of the technical program committee of several international conferences.

Antonio M. Peinado

Antonio M. Peinado

Research Focus & Metrics

Academic Career Length

Publication Type Breakdown

Representative Publications

About Me