2002 14th International Conference on Digital Signal Processing Proceedings. DSP 2002 (Cat. No.02TH8628)
Cơ quản chủ quản: N/A
Lĩnh vực:
Các bài báo tiêu biểu
Improving the speed and performance of adaptive equalizers via transform based adaptive filtering
Tập 2 - Trang 1301-1304 vol.2
Adaptive equalizers are widely used in many communication systems where the channel frequency response characteristics are either time varying or unknown such as the case in wireless and dial up telecommunication networks where the communication channel constantly change due to the different packet routes and switching that takes place, as well as due to the changes in the RF propagation. This wor......
#Adaptive equalizers #Adaptive filters #Discrete Fourier transforms #Discrete wavelet transforms #Fourier transforms #Discrete cosine transforms #Eigenvalues and eigenfunctions #Frequency response #Time varying systems #Communication channels
Probabilistic neural networks combined with GMMs for speaker recognition over telephone channels
Tập 2 - Trang 1081-1084 vol.2
We study the applicability of probabilistic neural networks (PNNs) as core classifiers to medium scale speaker recognition over fixed telephone networks. In particular, banking applications with up to 400 enrolled speakers and short training times are targeted. Two PNN-based open-set text-independent systems, for speaker identification and speaker verification, respectively, are presented. The per......
#Neural networks #Speaker recognition #Telephony #Mel frequency cepstral coefficient #Speech #Training data #Working environment noise #Laboratories #Banking #Wideband
Flexible real time signal filtering in space using reconfigurable logic
Tập 2 - Trang 849-852 vol.2
The High Performance Computing (HPC-I) payload is an innovative computing device designed for deployment on the Australian scientific mission satellite FedSat. HPC-I will validate and evaluate the practicality of using reconfigurable field programmable gate array (FPGA) technology in the space environment. The deployment of reconfigurable FPGA technology on-board satellites is a very promising sol......
#Filtering #Reconfigurable logic #Space technology #Finite impulse response filter #Field programmable gate arrays #High performance computing #Satellites #Payloads #Australia #Programmable logic arrays
Audio-visual speech recognition by speechreading
Tập 2 - Trang 1069-1072 vol.2
Speechreading increases intelligibility in human speech perception. This suggests that conventional acoustic-based speech processing can benefit from the addition of visual information. This paper exploits speechreading for joint audio-visual speech recognition. We first present a color-based feature extraction algorithm that is able to extract salient visual speech features reliably from a fronta......
#Speech recognition #Hidden Markov models #Humans #Speech processing #Feature extraction #Data mining #Video sequences #Maintenance #Streaming media #Audio-visual systems
Evaluating wavelet compression in microcalcification detection in mammography
Tập 2 - Trang 535-538 vol.2
The aim of this study is to evaluate the performance of a wavelet-based image compression algorithm in mammography. As microcalcifications detection is selected as diagnostic task, the algorithm is evaluated with respect to its visually lossless threshold at low compression ratios and not its supra-threshold performance. The threshold is determined by means of observer performance using a set of d......
#Mammography #Image coding #Image quality #Biomedical imaging #Compression algorithms #Testing #Medical diagnostic imaging #Degradation #Diseases #Tiles
Efficient calculation of a physiologically-motivated representation for sound
Tập 2 - Trang 587-590 vol.2
An algorithm is proposed which calculates a computationally efficient approximation of a certain physiologically-motivated representation for sound, called the summary autocorrelation function. This representation has been found very useful in several tasks, such as sound separation, multiple period estimation, and computational auditory scene analysis. However, it has been computationally too com......
#Auditory system #Psychoacoustic models #Autocorrelation #Band pass filters #Frequency estimation #Image analysis #Humans #Signal analysis #Performance analysis #Psychology
A timing recovery criterion derived from the tap weights of a decision feedback equalizer for QAM digital subscriber line systems
Tập 2 - Trang 1281-1284 vol.2
In this paper a timing recovery criterion is derived from the optimum feedforward coefficients of an adaptive symbol-spaced complex-valued decision feedback equalizer (DFE). The criterion is deduced by evaluating the relationship of sampling phase and corresponding, in the minimum mean square error (MMSE) sense optimum, equalizer tap weights exemplarily for a typical digital subscriber line (DSL) ......
#Decision feedback equalizers #Quadrature amplitude modulation #DSL #Sampling methods #Filters #Timing jitter #Field-flow fractionation #Signal to noise ratio #Signal processing #Transceivers
Scale hyperparameter estimation for GGMRF prior models with application to SPECT images
Tập 2 - Trang 521-524 vol.2
In this work we develop a Bayesian reconstruction method for SPECT (single photon emission computed tomography) images, using as prior GGMRF (generalized Gaussian Markov random fields) distributions and estimating the scale hyperparameter following the evidence analysis. Preconditioning methods are used to estimate this hyperparameter and the approximations used are compared on synthetic images.
#Image reconstruction #Degradation #Bayesian methods #Application software #Image analysis #Distributed computing #Optical computing #Reconstruction algorithms #Single photon emission computed tomography #Markov random fields
Visual speech recognition using support vector machines
Tập 2 - Trang 1093-1096 vol.2
In this paper we propose a visual speech recognition network based on support vector machines. Each word of the dictionary is described as a temporal sequence of visemes. Each viseme is described by a support vector machine, and the temporal character of speech is modeled by integrating the support vector machines as nodes into a Viterbi decoding lattice. Experiments conducted on a small visual sp......
#Speech recognition #Support vector machines #Mouth #Hidden Markov models #Dictionaries #Viterbi algorithm #Lattices #Active shape model #Real time systems #Informatics
ARMA modelling based on root cepstral deconvolution
Tập 2 - Trang 745-748 vol.2
Cepstral deconvolution has been successfully applied to many diverse fields, such as speech and seismic analysis. Thus far, all cepstral modelling performance has been empirical, relying on the judgement of the designer. A novel method for measuring root cepstral ARMA modelling performance is proposed, by introducing a cost function applied directly to the root cepstral domain. It is, therefore, p......
#Cepstral analysis #Deconvolution #Autoregressive processes #Cepstrum #Poles and zeros #Speech analysis #Wiener filter #Speech processing #Predictive models #Finite impulse response filter