While some first language (L1) reading models suggest that inefficient word recognition and small working memory tend to inhibit higher-level comprehension processes; the Compensatory Encoding Model maintains that slow word recognition and small working memory do not normally hinder reading comprehension, as readers are able to operate metacognitive strategies to compensate for inefficient word...

In this paper we present a hybrid recognition system that integrates hidden Markov models (HMM) with neural networks (NN) in a probabilistic framework. The input data is processed first by a lexicon–driven word recognizer based on HMMs to generate a list of the candidateN–best– scoring word hypotheses as well as the segmentation of such word hypotheses into characters. An NN classifier is used ...

In many speech recognition applications such as name dialing, it is necessary to have the ability to know when a recognition error has occurred so that undesired or unpredicted system behavior can be minimized. Con dence measure is usually used for detection of probable errors. In this paper, a new method for measuring condence is presented. The method is based on use of recursive mumble models...

Many text recognition systems recognize text imagery at the character level and assemble words from the recognized characters. An alternative approach is to recognize text imagery at the word level, without analyzing individual characters. This approach avoids the problem of individual character segmentation, and can overcome local errors in character recognition. A word-level recognition syste...

Many complex systems have been modeled as networks. Examples of such systems that are of interest to cognitive psychologists include the mental lexicon for spoken word recognition and semantic memory. A frequent finding in such studies is that the frequency distribution of the number of connections for each node in the network follows a power law. This finding has been interpreted to mean that ...

Recognition errors hinder the proliferation of speech recognition (SR) systems. Based on the observation that recognition errors may result in ungrammatical sentences, especially in dictation application where an acceptable level of accuracy of generated documents is indispensable, we propose to incorporate two kinds of linguistic features into error detection: lexical features of words, and sy...

Speech perception flexibly adapts to short-term regularities of ambient speech input. Recent research demonstrates that the function of an acoustic dimension for speech categorization at a given time is relative to its relationship to the evolving distribution of dimensional regularity across time, and not simply to a fixed value along the dimension. Two experiments examine the nature of this d...

We present a robust RTE approach which is built as one module incorporating all possible knowledge sources in form of different features. This way we can easily include or remove knowledge sources which are involved into the process of judging the entailment relation. We perform numerous tests in which we analyse the contribution of different types of features based on word forms, structural in...

Memory and speed are two key factors that must be faced when applying voice dialer to Pocket PCs. To provide a solution, a novel decoding method integrated with the score differences of token paths is proposed, named as “Dynamically-Adjustable Histogram Pruning”. Additionally, the computation of likelihood score is accelerated by means of dynamic score lookup table. Furthermore, a new acoustic ...