It is not possible to include all the words in a natural language for general text-to-speech system. Grapheme-tophoneme conversion system is essential to pronounce a word which is out of vocabulary. Grapheme-to-phoneme rules play a vital role where lexical lookup fails. Though basic Grapheme-tophoneme rules system is very simple yet it is very powerful for naturalness of a TTS system. Letter-to...

An automatic traffic sign detection system would be important in a driver assistance system. In this paper, an approach for detecting numbers on speed limit signs is proposed. Such a system would have to provide a high recognition performance in real-time. Thus, in this paper we propose to apply evolvable hardware for the classification of the numbers extracted from images. The system is based ...

In two experiments, we examined the acquisition and retention of a letter-detection skill with a consistent-mapping procedure. In Experiment 1, subjects were trained from 0 to 4 sessions at detecting the letter H in displays containing random letters, and retesting occurred after a 1-month delay. Performance improved and in some cases became more automatic, and the performance level was maintai...

A patient with spelling dyslexia read both words and text accurately but slowly and laboriously letter by letter. Her performance on a test of lexical decision was slow. She had great difficulty in detecting a 'rogue' letter attached to the beginning or end of a word--for example, ksong--or in parsing two unspaced words, such as applepeach. By contrast she was immune to the effects of interpola...

Over the years, face detection and recognition has attracted attention of many researchers and scientists. Many efforts has been done to built a fully automatic system capable of detecting and recognizing faces. The applications of such a system are numerous, from automated security systems, census, intelligence information etc. In this report, I present my experience with implementation of neu...

This paper describes the improvement of an automatic system for detecting semantic relations between nominals by the use of linguistically motivated knowledge combined with machine learning techniques. A previous version of the system using a Support Vector Machine classifier was evaluated in the 4 International Workshop on Semantic Evaluations, SEMEVAL [5]. The performance of the system improv...

We present a novel approach for improving communication success between users of speech-to-speech translation systems by automatically detecting errors in the output of automatic speech recognition (ASR) and statistical machine translation (SMT) systems. Our approach initiates system-driven targeted clarification about errorful regions in user input and repairs them given user responses. Our sy...