Proceedings ArticleDOI
Toward a massively parallel system for word recognition
Maurice K. Wong,Hon Wai Chun +1 more
- Vol. 11, pp 1967-1970
Reads0
Chats0
TLDR
A linguistic knowledge base is built into the network, allowing both data-driven processing and top-down prediction to cooperate or compete in working toward the correct lexical hypothesis.Abstract:
This paper describes a massively parallel system for word recognition. Based on the connectionist network model adopted from cognitive science and artificial intelligence, the system consists of a large number of simple neuron-like processing units, or nodes, which represent words, phonetic segments, or phonetic features. The computation consists of constant updating of activation levels of all nodes, resulting from the excitatory links and inhibitory links between the nodes. Input to the system consists of frame-by-frame scores of similarity to a set of pre-defined spectral filters, which represents the set of phonetic segments necessary for distinguishing between words in the vocabulary. These similarity scores are combined into phonetic feature indexes for each frame of speech as input to the feature nodes in the network. A linguistic knowledge base is built into the network, allowing both data-driven processing and top-down prediction to cooperate or compete in working toward the correct lexical hypothesis.read more
Citations
More filters
Journal ArticleDOI
Review of neural networks for speech recognition
TL;DR: Further work is necessary for large-vocabulary continuous-speech problems, to develop training algorithms that progressively build internal word models, and to develop compact VLSI neural net hardware.
Proceedings ArticleDOI
A neural net approach to speech recognition
TL;DR: The Viterbi net as mentioned in this paper is a neural network implementation of the hidden Markov models (HMMs) used very effectively in recognition systems based on Hidden Markov Models (HMM).
Proceedings Article
Network regions: alternatives to the winner-take-all structure
TL;DR: This paper offers an alternative competition model based upon a meta-network representation scheme called network regions that are analogous to net spaces in partitioned semantic networks that can be used in many ways to clarify the representational structure in massively parallel networks.
Proceedings Article
A Representation for Temporal Sequence and Duration in Massively Parallel Networks.
TL;DR: This paper describes a novel scheme which provides massively parallel models with the ability to represent and recognize temporal constraints such as sequence and duration by exploiting link to link interactions.
Proceedings Article
A representation for temporal sequence and duration in massively parallel networks: exploiting link interactions
TL;DR: In this article, the authors describe a novel scheme which provides massively parallel models with the ability to represent and recognize temporal constraints such as sequence and duration by exploiting link to link interactions.
References
More filters
Journal ArticleDOI
The TRACE model of speech perception.
TL;DR: The TRACE model, described in detail elsewhere, deals with short segments of real speech, and suggests a mechanism for coping with the fact that the cues to the identity of phonemes vary as a function of context.
Journal ArticleDOI
Connectionist Models and Their Properties
TL;DR: A general connectionist model is introduced and how it might be used in cognitive science is considered, among the issues addressed are: stability and noise-sensitivity, distributed decision-making, time and sequence problems, and the representation of complex concepts.
Book
Connectionist models and their properties
TL;DR: In this article, the authors introduce a general connectionist model and consider how it might be used in cognitive science, including stability and noise-sensitivity, distributed decision-making, time and sequence problems, and representation of complex concepts.
Journal ArticleDOI
Massively Parallel Parsing: A Strongly Interactive Model of Natural Language Interpretation*
David L. Waltz,Jordan Pollack +1 more
TL;DR: This work describes a parallel model for the representation of context and of the priming of concepts in a natural language processing system with modular knowledge sources but strongly interactive processing.
Journal ArticleDOI
Speech perception: a model of acoustic–phonetic analysis and lexical access
TL;DR: The LAFS (Lexical Access From Spectra) model is proposed here as a response to issues of acoustic analysis and lexical search; it combines expected phonological and acoustic-phonetic properties of English word sequences into a simple spectral-sequence decoding network structure.