This paper describes a method of generating effective language models for voice query recognition and a new dialogue strategy for a voice activated QA system. By using multiple domain language models, better recognition accuracy is obtained for query utterances. In the proposed interactive dialogue strategy using multimodal user interface, users are requested to indicate correct keywords and in...

In this paper, we present the Arabic handwriting recognition system that was submitted to the 2013 NIST Open Handwriting Recognition and Translation Evaluation (OpenHaRT 2013). Our baseline recognition system is based on Hidden Markov Models and we also propose a lattice-based framework to combine the outputs from several different recognition engines. Keywords—Document recognition, Arabic hand...

In this study, we make a scheme to explore the importance of modification relation for the emotional keywords annotation and emotion types recognition. We extract three modification features which are degree words, negative words and conjunctions from the Chinese emotion corpus named Ren-CECps. Beside word and part-ofspeech, three modification relations are adopted as feature in this study. We ...

-An algorithm is presented for keyword recognition in Oriental language document images. The objective is to recognize keywords composed of more than one consecutive character in document images where there are no explicit visually defined word boundaries. The technique exploits the redundancy expressed by the difference between the number of possible character strings of a fixed length and the...