Simple Speech Recognition with Little Linguistic Creatures

M.F.J. Drossaers, D.A. Dokter

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    10 Downloads (Pure)


    In this paper we present a stochastic neural­network architecture, the synchronous-network acceptor, that can approximately simulate nonde­ terministic finite-state automata, where the preci­sion of the approximation depends on the level of noise in the synchronous-network acceptor. This network learns to simulate finite-state automata by means of an unsupervised learning algorithm. The synchronous-network acceptor is a neuro­physiologically plausible model of connected relay nuclei, or connected, coherent, collections of cor­tical columns. The learning algorithm is a plausi­ble model of a column formation process or, more generally, an axon terminal segregation process.
    Complex self-organizing systems can be con­structed as ensembles of synchronous-network ac­ceptors. In virtue of the fact that finite-state automata can be simulated, applications of such systems can be implementations of linguistic the­ories, for instance parsing algorithms. However, we prefer a reductionistic, holistic approach. The approach is reductionist in that linguistic behav­ior is studied via its neurophysiological substrate.
    Our approach is holistic because we consider com­plete linguistic systems. These systems are called little linguistic creatures. They typically contain models of nervous sensory, motivational, and mo­tor subsystems, and unlike in more conventional approaches in which various linguistic faculties are studied separately, we reduce the complexity of the subject by modeling simple linguistic sys­tems. This holistic approach should in the end have the advantage of domain independence over more conventional approaches.
    The system of self-organizing synchronous network acceptors we present in this paper is a very simple linguistic creature for speech recog­nition. Its state provides the semantics of the linguistic input and the context information for
    the resolution of nondeterministic choices.
    Original languageEnglish
    Title of host publicationSpeech and Language Engineering
    Subtitle of host publicationProceedings of the eighth Twente Workshop on Language Technology
    EditorsL. Boves, A. Nijholt
    Place of PublicationEnschede
    PublisherUniversity of Twente
    Publication statusPublished - 12 Dec 1994
    EventTwente Workshop on Language Technology, TWLT 8 - Enschede, the Netherlands
    Duration: 1 Dec 19942 Dec 1994

    Publication series

    NameTwente Workshop on Language Technology
    PublisherUniversity of Twente
    ISSN (Print)0929-0672


    WorkshopTwente Workshop on Language Technology, TWLT 8
    OtherDecember 1-2, 1994

    Fingerprint Dive into the research topics of 'Simple Speech Recognition with Little Linguistic Creatures'. Together they form a unique fingerprint.

    Cite this