{"title":"On the performance of subspace methods with array model errors and spatial smoothing","authors":"K. Hari, Uma Gummadavelli","doi":"10.1109/ICASSP.1993.319667","DOIUrl":"https://doi.org/10.1109/ICASSP.1993.319667","url":null,"abstract":"The effect of spatial smoothing (forward smoothing and forward-backward smoothing) on the performance of subspace methods in the presence of array model errors for direction-of-arrival (DOA) estimation is studied. Theoretical expressions for the mean squared error (MSE) in DOA are obtained, based on a common framework of analysis. Simulations were carried out to substantiate the theory developed. For the cases considered, smoothing improves the performance of the ESPRIT and minimum-norm method while it is not so for the multiple signal classification (MUSIC) technique.<<ETX>>","PeriodicalId":428449,"journal":{"name":"1993 IEEE International Conference on Acoustics, Speech, and Signal Processing","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121596829","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Hybrid neural-network/HMM approaches to wordspotting","authors":"R. Lippmann, E. Singer","doi":"10.1109/ICASSP.1993.319181","DOIUrl":"https://doi.org/10.1109/ICASSP.1993.319181","url":null,"abstract":"Two approaches to integrating neural network and hidden Markov model (HMM) algorithms into one hybrid wordspotter are being explored. One approach uses neural network secondary testing to analyze putative hits produced by a high-performance HMM wordspotter. This has provided consistent but small reductions in the number of false alarms required to obtain a given detection rate. In one set of experiments using the NIST Road Rally database, secondary testing reduced the false alarm rate by an average of 16.4%. A second approach uses radial basis function (RBF) neural networks to produce local machine scores for a Viterbi decoder. Network weights and RBF centers are trained at the word level to produce a high score for the correct keyword hits and a low score for false alarms generated by nonkeyword speech. Preliminary experiments using this approach are exploring a constructive approach which adds RBF centers to model nonkeyword near-misses and a cost function which attempts to maximize directly average detection accuracy over a specified range of false alarm rates.<<ETX>>","PeriodicalId":428449,"journal":{"name":"1993 IEEE International Conference on Acoustics, Speech, and Signal Processing","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121767083","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Bootstrap multiple tests with variance stabilization: application to optimal sensor location","authors":"A. Zoubir","doi":"10.1109/ICASSP.1993.319580","DOIUrl":"https://doi.org/10.1109/ICASSP.1993.319580","url":null,"abstract":"The author reviews and discusses bootstrap methods for testing parameters in situations where sample size tends to be small or the distribution of the test statistic cannot be derived analytically. A bootstrap based variance stabilizing transformation for the parameter under test is considered. This procedure is crucial if the test is to have good power properties and also for the accuracy of the test level. These techniques are applied for comparing multiple coherences, a test which arises in finding optimal sensor locations for knock detection in spark ignition engines. Simulation and experimental results are presented as obtained on a test bed. The tests proposed are multiple tests and permit the finding of optimal positions for sensor groups to control knock in several cylinders at various rotation speeds.<<ETX>>","PeriodicalId":428449,"journal":{"name":"1993 IEEE International Conference on Acoustics, Speech, and Signal Processing","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131971004","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. Baskurt, F. Peyrin, H. Benoit-Cattin, R. Goutte
{"title":"Coding of 3D medical images using 3D wavelet decompositions","authors":"A. Baskurt, F. Peyrin, H. Benoit-Cattin, R. Goutte","doi":"10.1109/ICASSP.1993.319873","DOIUrl":"https://doi.org/10.1109/ICASSP.1993.319873","url":null,"abstract":"The use of a 3-D wavelet transform (WT) for the compression of 3-D medical images is investigated. A 3-D separable WT is applied using, for each direction, a pair of conjugate quadrature filters allowing perfect reconstruction. For each level of resolution, eight subimages are obtained, and a specific coding procedure using a 3-D discrete cosine transform is applied. The first results obtained on 3-D magnetic resonance imaging (MRI) images of a human heart are presented.<<ETX>>","PeriodicalId":428449,"journal":{"name":"1993 IEEE International Conference on Acoustics, Speech, and Signal Processing","volume":"218 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131983547","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Multi-rate video coding using pruned tree-structured vector quantization","authors":"Ligang Lu, W. Pearlman","doi":"10.1109/ICASSP.1993.319795","DOIUrl":"https://doi.org/10.1109/ICASSP.1993.319795","url":null,"abstract":"A low-rate video coding scheme which uses pruned tree-structured vector quantization (PTSVQ) is introduced. Designed by optimally growing the tree to a large rate and then pruning back to lower rates, PTSVQ is both a multirate and a variable rate coding technique. Since it has more flexibility than full-search VQ and fixed-rate tree-structured VQ, it is able to perform better. Furthermore, the tree structure reduces the computational complexity. Incorporated with the motion compensation and the quadtree decomposition techniques, the system achieves very good performance by exploiting the spatial and the temporal correlations of the images, as well as the regional statistics characteristic of the motion-compensated frame difference signal.<<ETX>>","PeriodicalId":428449,"journal":{"name":"1993 IEEE International Conference on Acoustics, Speech, and Signal Processing","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134044542","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Eliminating distortion in the Beylkin-Coifman-Rokhlin transform","authors":"J. R. O'Hair, B. Suter","doi":"10.1109/ICASSP.1993.319501","DOIUrl":"https://doi.org/10.1109/ICASSP.1993.319501","url":null,"abstract":"A systematic approach is presented for the elimination of distortion in the Beylkin-Coifman-Rokhlin (BCR) transform, a technique that requires only O(N) operations to apply an N*N matrix to an arbitrary vector. Since these matrices and vectors are of finite length, implementations of the BCR transform require the application of some extension technique, and these extension methods result in an additional O(N) nonzero terms. The resulting algorithm retains O(N) complexity while eliminating all distortion in a perfect reconstruction sense. The only distortion remaining is in the wavelet coefficients, and that is due to the particular extension method chosen.<<ETX>>","PeriodicalId":428449,"journal":{"name":"1993 IEEE International Conference on Acoustics, Speech, and Signal Processing","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133868128","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Spatial-domain 2-D filter design using the Fornasini-Marchesini second model","authors":"T. Hinamoto","doi":"10.1109/ICASSP.1993.319867","DOIUrl":"https://doi.org/10.1109/ICASSP.1993.319867","url":null,"abstract":"A two-dimensional (2-D) Lyapunov equation with constant coefficients is considered for the Fornasini-Marchesini (FM) second local state-space (LSS) model. First, a condition is given that sufficiently guarantees the asymptotic stability. A technique is then developed in the spatial domain for the design of 2-D state-space digital filters with guaranteed asymptotic stability. This is done by incorporating the above stability condition into the 2-D filter structure. A numerical example is solved to illustrate the utility of the proposed technique.<<ETX>>","PeriodicalId":428449,"journal":{"name":"1993 IEEE International Conference on Acoustics, Speech, and Signal Processing","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131537739","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Linear estimation of moments for non-stationary signals","authors":"P. Y. Wu, H. Lev-Ari","doi":"10.1109/ICASSP.1993.319683","DOIUrl":"https://doi.org/10.1109/ICASSP.1993.319683","url":null,"abstract":"The behavior of linear estimation of moments in a non-stationary environment is analyzed. A quantitative performance measure is introduced to evaluate the performance of these estimators. Optimal estimators are derived and their performance is compared with that of conventional (exponentially-windowed) moment estimators.<<ETX>>","PeriodicalId":428449,"journal":{"name":"1993 IEEE International Conference on Acoustics, Speech, and Signal Processing","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131586142","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Recursive least squares problem implementation on a generalized interconnection of DSP processors","authors":"Sati Banerjee, P. Chau","doi":"10.1109/ICASSP.1993.319563","DOIUrl":"https://doi.org/10.1109/ICASSP.1993.319563","url":null,"abstract":"The problem of implementing a recursive least squares (RLS) problem on a multiprocessor network comprising general-purpose digital signal processor is addressed. As an example of an application scenario, the adaptive beamforming problem has been chosen, where an RLS formulation has been adopted for obtaining the optimum weights. Although optimal array processors have been proposed for this problem, implementation on a generalized network affords a flexible as well as a modular and reconfigurable solution, suitable for a highly dynamic environment with changing applications and problem sizes. The parallelization issues are explored and a scheme for an efficient implementation is described. An implementation of the minimum-variance distortionless response (MVDR) problem on a network of DSP32C processors is evaluated. A 1024 size problem implementation is evaluated with the DSP32C as the computation engine, and it is shown that, when the number of processors in the system is constrained to be 10, near-optimal performance can be attained with four processors. Thus, this approach is a useful aid in determining optimal system performance parameters.<<ETX>>","PeriodicalId":428449,"journal":{"name":"1993 IEEE International Conference on Acoustics, Speech, and Signal Processing","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131815488","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Improving Prony's estimator for multiple frequency estimation by a general method of parametric filtering","authors":"Ta‐Hsin Li, B. Kedem","doi":"10.1109/ICASSP.1993.319643","DOIUrl":"https://doi.org/10.1109/ICASSP.1993.319643","url":null,"abstract":"Prony's estimator is known to be inconsistent for frequency estimation. In an attempt to diminish this problem, Dragosevic and Stankovic (1989) coupled the least squares method of autoregressive (AR) estimation with an iterative filtering scheme using an all-pole filter. But the inconsistency still persists. It is shown that the method becomes consistent if an appropriately parametrized filter is employed. The all-pole filter in particular can be reparametrized so that it too satisfies the parametrization requirement and thus leads to consistent estimates. Experimental results show that the modified method has a higher resolution than the discrete Fourier transform (DFT) and that its overall performance is quite remarkable.<<ETX>>","PeriodicalId":428449,"journal":{"name":"1993 IEEE International Conference on Acoustics, Speech, and Signal Processing","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130827045","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}