Learn More
Fusing the advantages of multiple acoustic features is important for the robustness of voice activity detection (VAD). Recently, the machine-learning-based VADs have shown a superiority to traditional VADs on multiple feature fusion tasks. However, existing machine-learning-based VADs only utilize shallow models, which cannot explore the underlying manifold(More)
Cloud computing technology enables developers spend much more time on application quality without considering computing resource constraint, load balancing and performance tuning, etc. It raises challenges along with the benefits it offers to software testing. This paper is motivated with the concerns on how to test the online web applications in a scalable(More)
Web service based business process has become the backbone of enterprise information system, and it is evolving all the time. Therefore, the process has to be tested thoroughly and repeatedly whenever it is changed. This paper proposes a model driven approach toward generating executable test case from the given business process. The approach is composite(More)
To reduce the cost and risk of the development of system of systems (SoS) by pre-evaluation before the SoS is built, a model-driven approach is proposed to evaluate the SoS based on its architecture, especially focused on measures of performance and effectiveness. In order to implement the pre-evaluation, the system architecture needs to be transformed to(More)
Recently, the deep-belief-networks (DBN) based voice activity detection (VAD) has been proposed. It is powerful in fusing the advantages of multiple features, and achieves the state-of-the-art performance. However, the deep layers of the DBN-based VAD do not show an apparent superiority to the shallower layers. In this paper, we propose a(More)
We propose a novel approach to addressing the adaptation effectiveness issue in parameter adaptation for deep neural network (DNN) based acoustic models for automatic speech recognition by adding one or more small auxiliary output layers modeling broad acoustic units, such as mono-phones or tied-state (often called senone) clusters. In scenarios with a(More)
Effective knowledge management of the testing process is the key to improve the quality of software testing. Knowledge management has different features in software testing. One of the most important research questions is how to effectively integrate the knowledge management with the software testing process so that the knowledge assets can be spread and(More)
In this study we analyzed the potential use of Pseudo-Polar FFT algorithm for image reconstruction of synthetic aperture radiometer, and developed an effective method to improve the image reconstruction accuracy and computational efficiency simultaneously. The advantage of the new algorithm is that it takes pseudo-polar grid instead of Cartesian grid to(More)
In this paper, we present a probabilistic framework for goal-driven spoken dialog systems. A new dynamic stochastic state (DS-state) is then defined to characterize the goal set of a dialog state at different stages of the dialog process. Furthermore, an entropy minimization dialog management (EMDM) strategy is also proposed to combine with the DS-states to(More)