The shape-adaptive discrete cosine transform (SA-DCT) transform can be computed on a support of arbitrary shape, but retains a computational complexity comparable to that of the usual separable block-DCT (B-DCT). Despite the near-optimal decorrelation and energy compaction properties, application of the SA-DCT has been rather limited, targeted nearly exclusively to video compression. In this paper, we present a novel approach to image filtering based on the SA-DCT. We use the SA-DCT in conjunction with the Anisotropic Local Polynomial Approximation-Intersection of Confidence Intervals technique, which defines the shape of the transform's support in a pointwise adaptive manner. The thresholded or attenuated SA-DCT coefficients are used to reconstruct a local estimate of the signal within the adaptive-shape support. Since supports corresponding to different points are in general overlapping, the local estimates are averaged together using adaptive weights that depend on the region's statistics. This approach can be used for various image-processing tasks. In this paper, we consider, in particular, image denoising and image deblocking and deringing from block-DCT compression. A special structural constraint in luminance-chrominance space is also proposed to enable an accurate filtering of color images. Simulation experiments show a state-of-the-art quality of the final estimate, both in terms of objective criteria and visual appearance. Thanks to the adaptive support, reconstructed edges are clean, and no unpleasant ringing artifacts are introduced by the fitted transform

Pointwise Shape-Adaptive DCT for High-Quality Denoising and Deblocking of Grayscale and Color Images

This paper presents a new feature extraction algorithm called power normalized Cepstral coefficients (PNCC) that is motivated by auditory processing. Major new features of PNCC processing include the use of a power-law nonlinearity that replaces the traditional log nonlinearity used in MFCC coefficients, a noise-suppression algorithm based on asymmetric filtering that suppresses background excitation, and a module that accomplishes temporal masking. We also propose the use of medium-time power analysis in which environmental parameters are estimated over a longer duration than is commonly used for speech, as well as frequency smoothing. Experimental results demonstrate that PNCC processing provides substantial improvements in recognition accuracy compared to MFCC and PLP processing for speech in the presence of various types of additive noise and in reverberant environments, with only slightly greater computational cost than conventional MFCC processing, and without degrading the recognition accuracy that is observed while training and testing using clean speech. PNCC processing also provides better recognition accuracy in noisy environments than techniques such as vector Taylor series (VTS) and the ETSI advanced front end (AFE) while requiring much less computation. We describe an implementation of PNCC using "online processing" that does not require future knowledge of the input.

/pdf/power-normalized-cepstral-coefficients-pncc-for-robust-4hlic3rj7n.pdf

Power-normalized cepstral coefficients (PNCC) for robust speech recognition

Design, analysis and experimental evaluation of block based transformation in MFCC computation for speaker recognition

MPEG-4 is the multimedia standard for combining interactivity, natural and synthetic digital video, audio and computer-graphics Typical applications are: internet, video conferencing, mobile videophones, multimedia cooperative work, teleteaching and games With MPEG-4 the next step from block-based video (ISO/IEC MPEG-1, MPEG-2, CCITT H261, ITU-T H263) to arbitrarily-shaped visual objects is taken This significant step demands a new methodology for system analysis and design to meet the considerably higher flexibility of MPEG-4 Motion estimation is a central part of MPEG-1/2/4 and H261/H263 video compression standards and has attracted much attention in research and industry, for the following reasons: it is computationally the most demanding algorithm of a video encoder (about 60-80% of the total computation time), it has a high impact on the visual quality of a video encoder, and it is not standardized, thus being open to competition Algorithms, Complexity Analysis, and VLSI Architectures for MPEG-4 Motion Estimation covers in detail every single step in the design of a MPEG-1/2/4 or H261/H263 compliant video encoder: Fast motion estimation algorithms Complexity analysis tools Detailed complexity analysis of a software implementation of MPEG-4 video Complexity and visual quality analysis of fast motion estimation algorithms within MPEG-4 Design space on motion estimation VLSI architectures Detailed VLSI design examples of (1) a high throughput and (2) a low-power MPEG-4 motion estimator Algorithms, Complexity Analysis and VLSI Architectures for MPEG-4 Motion Estimation is an important introduction to numerous algorithmic, architectural and system design aspects of the multimedia standard MPEG-4 As such, all researchers, students and practitioners working in image processing, video coding or system and VLSI design will find this book of interest

Algorithms, Complexity Analysis and VLSI Architectures for MPEG-4 Motion Estimation

1. Random Variables and Stochastic Processes

This paper presents several strategies to improve the performance of very low bit rate speech coders and describes a speech codec that incorporates these strategies and operates at an average bit rate of 1.2 kb/s. The encoding algorithm is based on several improvements in a mixed multiband excitation (MMBE) linear predictive coding (LPC) structure. A switched-predictive vector quantiser technique that outperforms previously reported schemes is adopted to encode the LSF parameters. Spectral and sound specific low rate models are used in order to achieve high quality speech at low rates. An MMBE approach with three sub-bands is employed to encode voiced frames, while fricatives and stops modelling and synthesis techniques are used for unvoiced frames. This strategy is shown to provide good quality synthesised speech, at a bit rate of only 0.4 kb/s for unvoiced frames. To reduce coding noise and improve decoded speech, spectral envelope restoration combined with noise reduction (SERNR) postfilter is used. The contributions of the techniques described in this paper are separately assessed and then combined in the design of a low bit rate codec that is evaluated against the North American Mixed Excitation Linear Prediction (MELP) coder. The performance assessment is carried out in terms of the spectral distortion of LSF quantisation, mean opinion score (MOS), A/B comparison tests and the ITU-T P.862 perceptual evaluation of speech quality (PESQ) standard. Assessment results show that the improved methods for LSF quantisation, sound specific modelling and synthesis and the new postfiltering approach can significantly outperform previously reported techniques. Further results also indicate that a system combining the proposed improvements and operating at 1.2 kb/s, is comparable (slightly outperforming) a MELP coder operating at 2.4 kb/s. For tandem connection situations, the proposed system is clearly superior to the MELP coder.

/pdf/strategies-to-improve-the-performance-of-very-low-bit-rate-2pgfz0l3k4.pdf

Strategies to improve the performance of very low bit rate speech coders and application to a variable rate 1.2 kb/s codec

In this paper, a text-independent automatic speaker recognition (ASkR) system is proposed-the SR/sub Hurst/-which employs a new speech feature and a new classifier. The statistical feature pH is a vector of Hurst (H) parameters obtained by applying a wavelet-based multidimensional estimator (M/spl I.bar/dim/spl I.bar/wavelets ) to the windowed short-time segments of speech. The proposed classifier for the speaker identification and verification tasks is based on the multidimensional fBm (fractional Brownian motion) model, denoted by M/spl I.bar/dim/spl I.bar/fBm. For a given sequence of input speech features, the speaker model is obtained from the sequence of vectors of H parameters, means, and variances of these features. The performance of the SR/sub Hurst/ was compared to those achieved with the Gaussian mixture models (GMMs), autoregressive vector (AR), and Bhattacharyya distance (dB) classifiers. The speech database-recorded from fixed and cellular phone channels-was uttered by 75 different speakers. The results have shown the superior performance of the M/spl I.bar/dim/spl I.bar/fBm classifier and that the pH feature aggregates new information on the speaker identity. In addition, the proposed classifier employs a much simpler modeling structure as compared to the GMM.

Text-independent speaker recognition based on the Hurst parameter and the multidimensional fractional Brownian motion model

A new wavelet-based denoising scheme for speech enhancement applications is proposed. The new approach uses a neural network to estimate the threshold to be applied to the detail coefficients after wavelet decomposition. The proposed method is compared to classical wavelet-based denoising techniques in the presence of additive white Gaussian noise. Results are presented in terms of SNR gain as well as error rate performance in a speaker verification system. Especially in terms of SNR improvement, the proposed scheme has outperformed other wavelet-based speech enhancement techniques.

Wavelet denoising of speech using neural networks for threshold selection

In this paper, we describe several important experiments concerning large vocabulary distributed continuous speech recognition (LVDCSR) systems in Brazilian Portuguese using LSF and LPC - derived features. The ITU-T G.723.1 codec is employed and investigated as a case of practical use of this technology. Results are presented for both speaker dependent and independent modes as well as the situations where the same text or different texts were used for training and testing.

LSF and LPC - derived features for Large Vocabulary Distributed Continuous Speech Recognition in Brazilian Portuguese

Este trabalho tem por objetivo principal a construcao de um conjunto de vinte listas de dez frases foneticamente balanceadas para o portugues falado no Rio de Janeiro. Para o estabelecimento das listas de frases procedeu-se a um levantamento previo da frequencia relativa dos fones no portugues falado no Rio de Janeiro, apresentado na primeira parte do trabalho. Foi utilizado como indicador do balanceamento das frases o valor da distância qui-quadrado (χ2) observada entre a frequencia dos fones em cada uma das listas e sua ocorrencia na lingua falada. Uma da aplicacoes principais das listas de frases balanceadas reside na avaliacao subjetiva da qualidade de voz processada por codificadores digitais.

Abraham Alcaim

Papers

Strategies to improve the performance of very low bit rate speech coders and application to a variable rate 1.2 kb/s codec

Text-independent speaker recognition based on the Hurst parameter and the multidimensional fractional Brownian motion model

Wavelet denoising of speech using neural networks for threshold selection

LSF and LPC - derived features for Large Vocabulary Distributed Continuous Speech Recognition in Brazilian Portuguese

Freqüência de Ocorrência dos Fones e Listas de Frases Foneticamente Balanceadas no Português Falado no Rio de Janeiro DOI: 10.14209/jcis.1992.2