Scheduled System Maintenance
On Wednesday, July 26, IEEE Xplore will undergo scheduled maintenance from 1:00-3:00 PM ET.
During this time, there may be intermittent impact on performance. We apologize for any inconvenience.
By Topic

Speech, Image Processing and Neural Networks, 1994. Proceedings, ISSIPNN '94., 1994 International Symposium on

13-16 April 1994

Filter Results

Displaying Results 1 - 25 of 202
  • Proceedings of ICSIPNN '94. International Conference on Speech, Image Processing and Neural Networks

    Publication Year: 1994
    Request permission for commercial reuse | PDF file iconPDF (151 KB)
    Freely Available from IEEE
  • Vector quantization view of ΣΔ modulation

    Publication Year: 1994, Page(s):201 - 204 vol.1
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (272 KB)

    We analyze the behavior of a single-loop ΣΔ modulator using a vector quantization (VQ) approach. We extract the encoder-decoder structure typical of VQ, existing in a ΣΔ modulator. The study of the encoding part gives the intrinsic behavior of the modulator. Bounds to the intrinsic performance of the ΣΔ modulator can be derived through this approach in the overs... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Tunable time delay neural networks for isolated word recognition

    Publication Year: 1994, Page(s):105 - 108 vol.1
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (232 KB)

    In this article, we describe a new neural network structure and a corresponding new sequential training technique for speech recognition. The proposed system is a modification of the original time delay neural network (TDNN) structure of Waibel (1989). The new structure consists of a group of sub-nets, and each isolated word to be recognized corresponds to at least one sub-net. Since each sub-net ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 3D object recognition using qualitative features

    Publication Year: 1994, Page(s):205 - 208 vol.1
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (220 KB)

    We present a vision system that can be to recognize 3D objects. Surfaces are characterized by surface curvature. Qualitative features are shown to be effective in pruning the search space of possible scene interpretations explored by the recognition and localization technique. Within this paradigm, we implemented a system which extracts planar patches, and patches of quadrics of revolution from a ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A speech-text retrieval system using semantic data of the English/Japanese conversational texts

    Publication Year: 1994, Page(s):599 - 602 vol.2
    Cited by:  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (228 KB)

    A speech-text retrieval system is proposed. It is a text retrieving system using semantic data of conversational speech text. The textbase of the system has three types of data; English text, Japanese text and the SD-Form as the semantic data. A prototype system was implemented on a standard workstation View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new method of identifying occlusion and specular highlights using active vision

    Publication Year: 1994, Page(s):437 - 440 vol.2
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (224 KB)

    Occlusion and specular highlights are two fundamental problems in 3D computer vision. Their presence complicates the process of camera vergence, stereo matching and 3D reconstruction. The paper presents a new method of identifying occlusion and specular highlights using active vision. In the method, active camera movement is employed not in solving stereo correspondences, but to help in the identi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Research and implementation of text-to-speech system for Chinese

    Publication Year: 1994, Page(s):583 - 586 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (152 KB)

    The paper mainly introduces research based on a phonetic word-cutting algorithm and prosodic rules. An unlimited vocabulary text-to-speech system is introduced, which can output phoneme from texts stored in computer View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A novel algorithm for the restoration of AFM/STM images

    Publication Year: 1994, Page(s):784 - 787 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (328 KB)

    Images generated from the scanning tunneling microscope (STM) or atomic force microscope (AFM) imaging system can show microstructures of samples. However, resulting AFM/STM images are sometimes corrupted by streaks. Thus, to suppress such streaks becomes an important task in the processing of AFM/STM images. We analyze the generation of streaks, introduce a degradation model of the corrupted AFM/... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Study and implement of parallel algorithms in image processing based on YH supercomputer

    Publication Year: 1994, Page(s):757 - 759 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (104 KB)

    Studies the parallel algorithms in image processing based on the YH supercomputer, and pay attention to the parallel algorithms of image enhancement and edge detection. These algorithms are programmed in VECTAN. The experiment results show the general speed up ratio of edge detection is 2~8, the speed up ratio of image enhancement is about 20. It greatly increases the speed of image processing View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Speech trajectory recognition in SOFM by using Bayes theorem

    Publication Year: 1994, Page(s):109 - 112 vol.1
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (212 KB)

    Trajectory of a speech signal on a self-organizing feature map (SOFM) is usually obtained by concatenating the cells with peak neural excitation given each input vector. This usually causes unsmooth trajectory of speech. We introduce a new method, solidly grounded on Bayes rule, to find the response trajectory in SOFM. It takes into account not only the present response of the cells given input ve... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Corpus-based speech and language research in the Institute of Systems Science

    Publication Year: 1994, Page(s):142 - 145 vol.1
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (292 KB)

    This paper describes the ongoing and planned research projects on speech and language modeling in the Institute of Systems Science. Four main areas of work have been concentrated and targeted: (1) intonation unit modeling using prosodic features; (2) identification and acquisition of lexical compounds; (3) stochastic dependency grammar parsing; and (4) factual information extraction. These researc... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Transient responses in dynamical neural models

    Publication Year: 1994, Page(s):229 - 232 vol.1
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (180 KB)

    The authors consider the input/output behavior of a realistic dynamical neural model in comparison to those typically used in artificial neural networks. They have found that such models duplicate well those behaviors seen in living neurons, displaying a range of behaviors commonly seen in a wide variety of nonlinear dynamical systems. This is not captured well by weighted sum/monotonic transfer f... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Low delay CELP coding at 8 kbps using classified voiced and unvoiced excitation codebooks

    Publication Year: 1994, Page(s):472 - 475 vol.2
    Cited by:  Patents (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (252 KB)

    This paper presents an 8 kbps low delay CELP coding scheme which has a one way delay less than 5 ms. In the proposed scheme, we classify the analyzed speech as either voiced or unvoiced segment. An adaptive pitch excitation codebook is used to generate voiced speech while a Gaussian stochastic codebook is used to generate unvoiced speech. To eliminate the roughness of synthetic speech without affe... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Advances in image/video signal processing

    Publication Year: 1994, Page(s):VIII - VIXI vol.1
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (248 KB)

    The video signal is a sequence of images that requires real-time operation and a great deal of bandwidth. Video signal processing deals with filtering, matrixing, conversion, composition, bridging, and most importantly, compression. Various approaches for real-time video signal processing are presented. The pros and cons together with recent advances for each approach are also discussed View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An application of the discrete Fourier transformation in simulating large neural networks

    Publication Year: 1994, Page(s):495 - 498 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (268 KB)

    This paper presents an application of the discrete Fourier transform (DFT) to calculate neural activities efficiently in simulating large biologically motivated neural nets. The experimental results demonstrate the DFT technique is more superior in performing calculation of the neural activity which reduces the time complexity to a theoretical order of O(nlog2, n), n being the number of... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A novel application of information theory to pattern recognition problems

    Publication Year: 1994, Page(s):209 - 212 vol.1
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (248 KB)

    This paper is concerned with the development of an algorithm for the assessment of information content of 2-D patterns encountered in practical pattern recognition problems. The technique developed is based on the fundamentals of information theory (i.e., the entropy) to assess the translational and rotational information content of patterns which can then be combined to provide for the assessment... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Generalization of hierarchical retinotopic networks using stochastic distortion models

    Publication Year: 1994, Page(s):381 - 384 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (256 KB)

    The generalization of hierarchical retinotopic networks is modeled as a type of probability measure called “tail probability” with a stochastic distortion field. Learning in the network memorizes the exemplars in terms of the distribution. Generalization in a hierarchical retinotopic network is characterized by the probability measure of multilevel events and decision making at each ab... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Efficient interconversion algorithm for PARCOR and LSP parameters

    Publication Year: 1994, Page(s):603 - 606 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (224 KB)

    The paper introduces an efficient algorithm for calculating line spectrum frequencies from PARCOR coefficients and vice versa. The algorithm employs a recursive technique to generate the line spectrum from PARCOR coefficients. In each recursion, a rotation and scaling operations on the complex frequency plane are required. The even and odd line spectrum frequencies are found to be the zero crosspo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A comparison of multi-layer neural networks and optimized nearest neighbor classifiers for handwritten digit recognition

    Publication Year: 1994, Page(s):312 - 315 vol.1
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (272 KB)

    The basic nearest neighbor classifier (NNC) is often inefficient for classification in terms of memory space and computing time if all training samples are used as prototypes. These problems can be solved by reducing the number of prototypes using clustering algorithms and optimizing the prototypes using a special neural network model. The author compares the performance of the multi-layer neural ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The fast algorithm for the finite length discrete wavelet transform

    Publication Year: 1994, Page(s):642 - 645 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (196 KB)

    The paper presents a structured algorithm for the finite length discrete wavelet transform. The analysis and synthesis filter matrices H, G can be decomposed in kronecker product form with cyclic block matrix and lower-triangle block matrix. The cyclic matrix can be implemented using FFT and the lower-triangle matrix is implemented straightforward. The arithmetic complexity of the algorithm is pri... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A solution to the generalized Duda and Hart problem using Fourier parameterization

    Publication Year: 1994, Page(s):441 - 444 vol.2
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (188 KB)

    In a classic paper, R.O. Duda and P.E. Hart (1972) solved the unboundedness and non-uniformity problems of the line Hough transform by introducing a modified ρ-θ parameterization. Unfortunately, no equivalent parameterization exists for curves. W. Lam et al. (1993) proposed the Fourier descriptor as the parameterized curve equation in a Hough transform. We show that all parameters in thi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Optimal bandwidth allocation of multiple VBR video sources with priorities

    Publication Year: 1994, Page(s):365 - 368 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (252 KB)

    Transmitting video over ATM networks with a variable-bit-rate coding technique aims to optimize performance and to improve channel efficiency. Particularly the two-layer coding schemes that separate the coded bits into two priority streams are well suited for the ATM standard. This is achieved by giving different access priorities of the shared buffer to the two streams. In the paper, the authors ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Speech synthesis using two-sided linear prediction parameters

    Publication Year: 1994, Page(s):587 - 590 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (156 KB)

    A two-sided linear prediction (TSLP) model is shown to have high prediction gain over the conventional linear prediction (LPC) model [David and Ramamurthi, 1991], while it requires fewer coefficients in modeling. Unfortunately, speech synthesis cannot use the TSLP model directly because it needs future samples which are not available in the process. Autoregressive spectral matching (ARSM) is propo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A solution to the dynamic range problem of pixel values in color image enhancement

    Publication Year: 1994, Page(s):772 - 775 vol.2
    Cited by:  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (160 KB)

    The whole process of image enhancement is rearranging the pixel values according to different criteria. The commonly used display range for color images is 8 bits per primary per pixel. In the enhanced image, those pixels, with primary values out of the 8-bit range, are simply clipped on the boundary for display. This process loses the details in some areas and present unnatural appearance. The pa... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Systolic array for binary multiplier

    Publication Year: 1994, Page(s):745 - 748 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (136 KB)

    A new systolic implementation is proposed for multiplication of two n-bit binary numbers. It greatly saves the array size compared to previous solutions, while the throughput is only slightly decreased. Therefore it is very suitable for VLSI array processors. The entire structure is connected in a pipeline View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.