ct 7 Discriminative training for hidden Markov models (HMMs) has been a central theme in speech recognition research for many years. 8 One most popular technique is minimum classiļ...
In this paper, we show how an eļ¬cient ant based algorithm, called API and initially designed to perform real parameter optimization, can be adapted to the diļ¬cult problem of Hi...
The processing of Japanese text is complicated by the fact that there are no word delimiters. To segment Japanese text, systems typically use knowledge-based methods and large lex...
In this paper, to provide a robot with information relative to structure of its environment, we propose a method to recognize types of structural corridor landmarks such as T-junct...
This paper presents an unsupervised segmentation method for feature sequences based on competitivelearning hidden Markov models. Models associated with the nodes of the Self-Organ...