The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
End-to-end speech recognition systems have been successfully implemented and have become competitive replacements for hybrid systems. A common loss function to train end-to-end systems is connectionist temporal classification (CTC). This method maximizes the log likelihood between the feature sequence and the associated transcription sequence. However there are some weaknesses with CTC training. The...
Recurrent neural networks (RNNs) have shown an ability to model temporal dependencies. However the problem of exploding or vanishing gradients has limited their application. In recent years, long short-term memory RNNs (LSTM RNNs) have been proposed to solve this problem, and have achieved excellent results. However, because of the large size of LSTM RNNs, they more easily suffer from overfitting,...
Exploiting sparseness in deep neural networks is an important method for reducing the computational cost. In this paper, we study neuron sparseness in deep neural networks for acoustic modeling. For the feed-forward stage, we only activate neurons whose input values are larger than a given threshold, and set the outputs of inactive nodes to zero. Thus, only a few nonzero outputs are fed to the next...
A sensor-network physical activity monitoring system (SAMS) using wearable sensors is presented. It classifies and tracks body activity in real time. The system adopts a service-oriented architecture for data acquisition, sensor actuation & control, and real-time service management. The activity recognition and tracking are carried out using two levels of approaches. At level 1, the movement and...
DDoS (distributed denial-of-service) attacks detection system deployed in source-end network is superior in perceiving and throttling attacks before dataflows enter Internet, comparing with that in victim network. However, the current existed works in source- end network are so fragile, lead to a high false-positive rate and false-negative rate. This paper proposes a novel approach using multi-stream...
This paper proposes a dynamic hidden Markov random field (DHMRF) model for foreground object and moving shadow segmentation in indoor video scenes. Given an image sequence, temporal dependencies of consecutive segmentation fields and spatial dependencies within each segmentation field are unified in the novel dynamic probabilistic model that combines the hidden Markov model (HMM) and the Markov random...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.