Learn More
AbsfrucfThe current state-of-the-art in large-vocabulary, continuous speech recognition is based on the use of hidden Markov models (HMM). In an attempt to improve over HMM performance, we developed a hybrid system that combines the advantages of neural networks and HMM using a multiple hypothesis (or N-best) paradigm. The connectionist component of the(More)
In this paper we show how continuous speech recognition methods can be used for character recognition, resulting in a technology that is language independent and does not require presegmentation of the data at the character and word levels. In multi-font experiments on the ARPA Arabic OCR Corpus an average character error rate of 1.9% is obtained using the(More)
We developed a faster search algorithm that avoids the use of the N-Best paradigm until after more powerful knowledge sources have been used. We found, however, that there was little or no decrease in word errors. We then showed that the use of the N-Best paradigm is still essential for the use of still more powerful knowledge sources, and for several other(More)
In this paper, we incorporate the Hierarchical Mixtures of Experts (HME) method of probability estimation, developed by Jordan [1], into an HMMbased continuous speech recognition system. The resulting system can be thought of as a continuous-density HMM system, but instead of using gaussian mixtures, the HME system employs a large set of hierarchically(More)
Untill recently, state-of-the-art, large-vocabulary, continuous speech recognition (CSR) has employed Hidden Markov Modeling (HMM) to model speech sounds. In an attempt to improve over HMM we developed a hybrid system that integrates HMM technology with neural networks. We present the concept of a "Segmental Neural Net" (SNN) for phonetic modeling in CSR.(More)
Previously, we had developed the concept of a Segmental Neural Net (SNN) for phonetic modeling in continuous speech recognition (CSR). This kind of neural network technology advanced the state-of-the-art of large-vocabulary CSR, which employs Hidden Marlcov Models (HMM), for the ARPA 1oo0-word Resource Management corpus. More Recently, we started porting(More)
In this paper, a novel navigation based on vision for wireless capsule endoscopies is proposed. The algorithm based on dark regions was improved by setting the Region of Interest (ROI) to limit the search coverage around the last navigation point, introducing the morphology method to eliminate diverticula and vesicae and raising the concept of position(More)
In order to find rules of disaster weather from the history data and provide some support for the weather forecast, rough set theory was introduced into the field and a weather data model based on it was built. The model included the processes of data discretization, attributes reduction and rules extracting. For the rules extracting a new method based on(More)
In this paper, a novel navigation method based on vision is proposed by integrating the advantages of watershed and pyramid segmentation methods. Using the idea of the continuity between two successive images, it is possible to give a reasonable advisory when the visual navigation fails. Besides that, we proposed to set a region of interest to accelerate(More)