1-6hit |
Hocheol JEON Taehwan KIM Joongmin CHOI
This paper proposes a proactive management system for the events that occur across multiple personal user devices, including desktop PCs, laptops, and smart phones. We implemented the Personal Event Management Service using Dynamic Bayesian Networks (PEMS-DBN) system that proactively executes appropriate tasks across multiple devices without explicit user requests by recognizing the user's device reuse intention, based on the observed actions of the user for specific devices. The client module of PEMS-DBN installed on each device monitors the user actions and recognizes user intention by using dynamic Bayesian networks. The server provides data sharing and maintenance for the clients. A series of experiments were performed to evaluate user satisfaction and system accuracy, and also the amounts of resource consumption during intention recognition and proactive execution are measured to ensure the system efficiency. The experimental results showed that the PEMS-DBN system can proactively provide appropriate, personalized services with a high degree of satisfaction to the user in an effective and efficient manner.
This paper presents an inversion algorithm for dynamic Bayesian networks towards robust speech recognition, namely DBNI, which is a generalization of hidden Markov model inversion (HMMI). As a dual procedure of expectation maximization (EM)-based model reestimation, DBNI finds the 'uncontaminated' speech by moving the input noisy speech to the Gaussian means under the maximum likelihood (ML) sense given the DBN models trained on clean speech. This algorithm can provide both the expressive advantage from DBN and the noise-removal feature from model inversion. Experiments on the Aurora 2.0 database show that the hidden feature model (a typical DBN for speech recognition) with the DBNI algorithm achieves superior performance in terms of word error rate reduction.
Since their inception almost fifty years ago, hidden Markov models (HMMs) have have become the predominant methodology for automatic speech recognition (ASR) systems--today, most state-of-the-art speech systems are HMM-based. There have been a number of ways to explain HMMs and to list their capabilities, each of these ways having both advantages and disadvantages. In an effort to better understand what HMMs can do, this tutorial article analyzes HMMs by exploring a definition of HMMs in terms of random variables and conditional independence assumptions. We prefer this definition as it allows us to reason more throughly about the capabilities of HMMs. In particular, it is possible to deduce that there are, in theory at least, no limitations to the class of probability distributions representable by HMMs. This paper concludes that, in search of a model to supersede the HMM (say for ASR), rather than trying to correct for HMM limitations in the general case, new models should be found based on their potential for better parsimony, computational requirements, and noise insensitivity.
Toru KUMAGAI Motoyuki AKAMATSU
This paper presents a method of predicting future human driving behavior under the condition that its resultant behavior and past observations are given. The proposed method makes use of a dynamic Bayesian network and the junction tree algorithm for probabilistic inference. The method is applied to behavior prediction for a vehicle assumed to stop at an intersection. Such a predictive system would facilitate warning and assistance to prevent dangerous activities, such as red-light violations, by allowing detection of a deviation from normal behavior.
Abdulrahman ALHARBY Hideki IMAI
Security protocols flaws represent a substantial portion of security exposures of data networks. In order to evaluate security protocols against any attack, formal methods are equipped with a number of techniques. Unfortunately, formal methods are applicable for static state only, and don't guarantee detecting all possible flaws. Therefore, formal methods should be complemented with dynamic protection. Anomaly detection systems are very suitable for security protocols environments as dynamic activities protectors. This paper presents an intrusion detection system that uses a number of different anomaly detection techniques to detect attacks against security protocols.
Takahiro SHINOZAKI Sadaoki FURUI
One of the most important issues in spontaneous speech recognition is how to cope with the degradation of recognition accuracy due to speaking rate fluctuation within an utterance. This paper proposes an acoustic model for adjusting mixture weights and transition probabilities of the HMM for each frame according to the local speaking rate. The proposed model is implemented along with variants and conventional models using the Bayesian network framework. The proposed model has a hidden variable representing variation of the "mode" of the speaking rate, and its value controls the parameters of the underlying HMM. Model training and maximum probability assignment of the variables are conducted using the EM/GEM and inference algorithms for the Bayesian networks. Utterances from meetings and lectures are used for evaluation where the Bayesian network-based acoustic models are used to rescore the likelihood of the N-best lists. In the experiments, the proposed model indicated consistently higher performance than conventional HMMs and regression HMMs using the same speaking rate information.