By Topic

International Conference on Acoustics, Speech, and Signal Processing,

23-26 May 1989

Filter Results

Displaying Results 1 - 25 of 711
  • A locus model of coarticulation in an HMM speech recognizer

    Publication Year: 1989, Page(s):97 - 100 vol.1
    Cited by:  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (324 KB)

    A novel type of hidden Markov model (HMM) has been developed to account explicitly for the context-dependent vowel acoustic transitions in consonant-vowel and vowel consonant phonetic environments. The major difference between this type of HMM and the standard Gaussian HMM is that the Gaussian mean vectors associated with the vowel HMM states, which are intended to model the vowel acoustic transit... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • ICASSP-89: 1989 International Conference on Acoustics, Speech and Signal Processing (IEEE Cat. No.89CH2673-2)

    Publication Year: 1989
    Request permission for commercial reuse | PDF file iconPDF (54 KB)
    Freely Available from IEEE
  • An order recursive algorithm for synthesizing linear recursive filters

    Publication Year: 1989, Page(s):1131 - 1133 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (149 KB)

    The author proposes an order recursive algorithm to compute efficiently the solution to the set of linear equations for finding the parameters of a recursive filter whose unit impulse response best approximates that of the prescribed ideal response. The algorithm requires only O(p/sup 2/) operations. The inherent structure of the coefficient matrix in the system of linear equations and the inversi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Knowledge based parallel recognition of handwritten alphanumerics

    Publication Year: 1989, Page(s):1807 - 1810 vol.3
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (238 KB)

    A novel knowledge-based parallel processing system has been designed for recognition of handwritten characters. With five quadtree-linked microprocessors, this system can extract features from the character image in four directions simultaneously. Through repetitive order-giving and information-gathering between the master and the slaves, the system can process the information at two levels: globa... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Improving speech recognition accuracy with contextual phonemes and MMI training

    Publication Year: 1989, Page(s):116 - 119 vol.1
    Cited by:  Patents (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (204 KB)

    The authors experiment with a combination of two methods previously proposed to improve the performance of their speech recognition system. One method is based on the definition of an improved system of phonetic units, which takes into account the most important coarticulation effects. This system has been defined using knowledge about coarticulation, and by studying the errors of a standard phone... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Consonant recognition by modular construction of large phonemic time-delay neural networks

    Publication Year: 1989, Page(s):112 - 115 vol.1
    Cited by:  Papers (79)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (300 KB)

    It is shown that neural networks for speech recognition can be constructed in a modular fashion by exploiting the hidden structure of previously trained phonetic subcategory networks. The performance of resulting larger phonetic nets was found to be as good as the performance of the subcomponent nets by themselves. This approach avoids the excessive learning times that would be necessary to train ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An improved sub-word based speech recognizer

    Publication Year: 1989, Page(s):108 - 111 vol.1
    Cited by:  Papers (11)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (328 KB)

    The authors describe a system for speaker-dependent speech recognition based on acoustic subword units. Several strategies for automatic generation of an acoustic lexicon are outlined. Preliminary tests have been performed on a small vocabulary. In these tests, the proposed system showed results comparable to those of whole-word-based systems View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Speaker independent phonetic transcription of fluent speech for large vocabulary speech recognition

    Publication Year: 1989, Page(s):441 - 444 vol.1
    Cited by:  Papers (11)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (164 KB)

    Results are presented of experiments on speaker independent phonetic transcription of fluent speech. The acoustic-phonetic model is a 38505-parameter continuously variable duration hidden Markov model which allows real-time phonetic transcription to be performed by means of a modified Viterbi algorithm. The model was trained on 3020 sentences from the TIMIT database. Testing was performed on the r... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A formula for least-squares projection and its application in image reconstruction

    Publication Year: 1989, Page(s):1602 - 1605 vol.3
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (232 KB)

    A novel method for the interpolation of sampled images is presented. It makes use of a recently discovered formula for the least-squares projection of an arbitrary function onto a repetitive basis. The proposed interpolation formula differs from standard techniques such as cubic spline convolution in that the image samples are modified by a discrete convolution operator prior to the reconstruction... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Characterization of spectral transitions with applications to acoustic sub-word segmentation and automatic speech recognition

    Publication Year: 1989, Page(s):104 - 107 vol.1
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (284 KB)

    A mathematical model has been developed for tracking spectral transitions within the spectral envelope of a speech signal. This technique incorporates linguistic knowledge into a mathematical framework to determine time-varying acoustic-phonetic features and describe formant transitions. The proposed model is quite robust and is capable of extracting not only rapid spectral movement, but also smoo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new sample-interpolation method for recovering missing speech samples in packet voice communications

    Publication Year: 1989, Page(s):381 - 384 vol.1
    Cited by:  Papers (8)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (220 KB)

    A sample-interpolation method based on pattern matching is proposed to reduce speech quality degradation caused by packet losses. This method is used together with packet interleaving, which simplifies the recovery of missing packets to the recovery of missing sample values. The interpolation method is evaluated by an opinion test. The results show that speech quality is satisfactory up to a packe... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A bit-level systolic architecture for very high performance IIR filters

    Publication Year: 1989, Page(s):2449 - 2452 vol.4
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (236 KB)

    A novel bit-level systolic array architecture for implementing bit-parallel IIR filter sections is presented. The authors have shown previously how the fundamental obstacle of pipeline latency in recursive structures can be overcome by the use of redundant arithmetic in combination with bit-level feedback. These ideas are extended by optimizing the degree of redundancy used in different parts of t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Toward a continuous model of the cortical column: Application to speech recognition

    Publication Year: 1989, Page(s):37 - 40 vol.1
    Cited by:  Papers (1)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (300 KB)

    The authors propose a novel approach to neuronlike models that consists in simulating cortical columns, i.e. associations of neurons having a specific, functional activity. This model is built according to a theory which is consistent with neurobiological data. The model is implemented through a network of columns that simulate the inherently parallel functioning of the nervous system. A descripti... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Recent advances in speech processing

    Publication Year: 1989, Page(s):429 - 440 vol.1
    Cited by:  Papers (12)  |  Patents (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1384 KB)

    An overview is given of recent advances in the domain of speech recognition. The author focuses on speech recognition, but also mentions some progress in other areas of speech processing (speaker recognition, speech synthesis, speech analysis and coding) using similar methodologies. The problems related to automatic speech processing are identified, and the initial approaches that have been follow... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A dedicated DSP computation engine based on VLSI vector signal processors

    Publication Year: 1989, Page(s):2564 - 2568 vol.4
    Cited by:  Papers (1)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (296 KB)

    A computation engine (V8) based on eight VLSI vector signal processors (ZSP-322) was developed for dedicated DSP (digital signal processing) applications in areas such as nonparametric spectral estimation, beamforming, Doppler, etc. A design methodology and a set of tools were implemented and tested, facilitating multiprocessor algorithm development and hardware implementation. A novel scheme for ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Model reduction for two-dimensional systems

    Publication Year: 1989, Page(s):1598 - 1601 vol.3
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (212 KB)

    A 2-D model reduction using singular perturbation methodology is presented. The strong-weak coupling effects that lead to eigenvalue clustering of A1 and A4 matrices are utilized to derive structure transformations for fast-slow decomposition. This in conjunction with an aggregation procedure given allows the development of reduced-order 2-D slow and fast su... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fast address generation for the computation of prime factor algorithms

    Publication Year: 1989, Page(s):1091 - 1094 vol.2
    Cited by:  Papers (6)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (312 KB)

    The authors propose an address generation scheme for in-place in-order prime factor algorithms. This scheme achieves high efficiency by using simple indirect addressing techniques to replace complicated modulo operations of previous methods. It is shown that the scheme is most suitable for software realizations using assembly languages. A hardware address generator based on this mapping scheme is ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The mean squared error criterion: Its effect on the performance of speech coders

    Publication Year: 1989, Page(s):77 - 80 vol.1
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (216 KB)

    Many speech coder designs use analysis-by-synthesis techniques in which a suitable output is chosen on the basis of mean squared error between input and output waveforms. A method is described for modeling the behavior of such coders, in an effort to discover what implications the use of this criterion has for the characteristics of the coders which use it. The model is used to show that as bit ra... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Real-time recognition of subword units on a hybrid multi-DSP/ASIC based acoustic front-end

    Publication Year: 1989, Page(s):101 - 103 vol.1
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (196 KB)

    A description is given of the hardware and software structure of the acoustic-phonetic decoding done in real time within the speaker-adaptive continuous speech understanding system SPICOS (Siemens, Philips, IPO continuous speech recognition and understanding). SPICOS is designed as a German language man-machine dialogue interface system consisting of acoustic-phonetic decoding, linguistic analysis... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The effects of non-stationary signal characteristics on the performance of adaptive audio restoration systems

    Publication Year: 1989, Page(s):377 - 380 vol.1
    Cited by:  Papers (3)  |  Patents (15)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (208 KB)

    The degrading effects of nonstationary and abruptly changing signal characteristics on the performance of a particular class of restoration systems, namely those which use two sources of information, are discussed. The system considered is the adaptive noise suppression system. In this system abrupt changes in signal statistics result in transient degradations in the form of excessive suppression ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Two-dimensional FIR filter architectures based on NTT

    Publication Year: 1989, Page(s):2445 - 2448 vol.4
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (248 KB)

    Two architectures suitable for programmable real-time two-dimensional finite-impulse-response (FIR) filters for a 512×512 pixel video system are presented. By applying the Winograd algorithm for an input data sequence of four pixels, the filtering rate is decimated by a factor of four and at the same time the required number of multiplications is reduced compared with conventional approaches... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Speech dynamics and recurrent neural networks

    Publication Year: 1989, Page(s):33 - 36 vol.1
    Cited by:  Papers (11)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (248 KB)

    Recently, connectionist models have been recognized as an interesting alternative tool to hidden Markov models for speech recognition. Their main property lies in their combination of good discriminating power and the ability to capture input-output relations. They have also been proved useful in dealing with statistical data. However, the serial aspect remains difficult to handle in that kind of ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A connectionist approach to continuous speech recognition

    Publication Year: 1989, Page(s):425 - 428 vol.1
    Cited by:  Papers (8)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (296 KB)

    The authors have applied connectionist learning procedures to speaker-independent continuous recognition, creating a system which has achieved 97% word accuracy and 91% sentence accuracy in preliminary tests on the TI/NBS connected-digits database. The system uses a four-layer back-propagation network with recurrent connections to generate and refine hypotheses about the identity of an utterance o... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A systolic IIR decimator

    Publication Year: 1989, Page(s):2560 - 2563 vol.4
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (208 KB)

    A discussion is presented of several methods of providing complex pole pairs in the transfer function of a decimator for oversampled converters. Utilization of pole cancellation with added compensating zeros yields a systolic structure that is easily implemented. Decomposition of the coefficient terms of the IIR decimator by means of a high radix modified Booths algorithm recording scheme is shown... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A group theoretical approach to filter design

    Publication Year: 1989, Page(s):1594 - 1597 vol.3
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (196 KB)

    The author investigates the following fundamental pattern recognition problem. He assumes that he has a set of signals or patterns, denoted by S, and an unknown pattern p. The problem is to decide if PS or pS. The author assumes further that S is symmetrical or regular in a group-theoretical sense. Harmonic analysis and the theory... View full abstract»

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