Meaningfulness and Trigram Recognition 1
نویسنده
چکیده
Recognition, after 1, 3, 6, 15, and 30 intervening events, for CCC and CVC trigrams of low, medium, and high meaningfulness (M) was studied in the Shepard-Teghtsoonian paradigm. Correct recognition varied directly with M and inversely with number of intervening events. False recognition varied inversely with M and increased with total number of presentations. Confidence in correct recognitions varied directly with M and inversely with number of intervening events, but remained stable over the experimental session. Confidence in"new'judgments of new trigrams declined sharply over the experimental session. Evidence is presented to the effect that false recognition is largely item specific and not a matter of general decision criterion.
منابع مشابه
Techniques for approximating a trigram language model
In this paper several methods are proposed for reducing the size of a trigram language model (LM), which is often the biggest data structure in a continuous speech recognizer, without a ecting its performance. The common factor shared by the di erent approaches is to select only a subset of the available trigrams, trying to identify those trigrams that mostly contribute to the performance of th...
متن کاملEstonian Large Vocabulary Speech Recognition System for Radiology
This paper describes implementation and evaluation of an Estonian large vocabulary continuous speech recognition system prototype for the radiology domain. We used a 44 million word corpus of radiology reports to build a word trigram language model. We recorded a test set of dictated radiology reports using ten radiologists. Using speaker independent speech recognition, we achieved a 9.8% word ...
متن کاملImproving trigram language modeling with the World Wide Web
We propose a novel method for using the World Wide Web to acquire trigram estimates for statistical language modeling. We submit an N-gram as a phrase query to web search engines. The search engines return the number of web pages containing the phrase, from which the N-gram count is estimated. The N-gram counts are then used to form web-based trigram probability estimates. We discuss the proper...
متن کاملCombination of a hidden tag model and a traditional n-gram model: a case study in czech speech recognition
A speech recognition system targeting high inflective languages is described that combines the traditional trigram language model and an HMM tagger, obtaining results superior to the trigram language model itself. An experiment in speech recognition of Czech has been performed with promising results. 1. Speech Recognition of Inflective Languages Inflective languages pose a hard problem in speec...
متن کاملEfficient lattice representation and generation
In large-vocabulary, multi-pass speech recognition systems, it is desirable to generate word lattices incorporating a large number of hypotheses while keeping the lattice sizes small. We describe two new techniques for reducing word lattice sizes without eliminating hypotheses. The first technique is an algorithm to reduce the size of non-deterministic bigram word lattices. The algorithm iterat...
متن کامل