Prosody-based affect recognition has great potential impact for building adaptive speech interfaces. For example, in intelligent systems for personalized learning, sensing a student's level of certainty, which is ...
详细信息
Prosody-based affect recognition has great potential impact for building adaptive speech interfaces. For example, in intelligent systems for personalized learning, sensing a student's level of certainty, which is often signaled prosodically, is one of the most interesting states to interpret and respond to. However, robust uncertainty recognition faces several challenges, including the lack of gold-standard labels, and differences in expressivity among speakers. In this paper we explore the intersection of these two issues. We have collected a corpus of spontaneous speech in a question-answering task. Three kinds of certainty labels are associated with each utterance. First, speakers rated their own level of certainty. Second, a panel of listeners rated how certain the speaker sounded. Third, an externally crowdsourced difficulty score is generated for each stimulus (the question). We present a word-level prosodic analysis of individual speaking styles, as they relate to these three different measurements of certainty. Our results suggest that instead of learning one-size-fits-all prosodic models of affect, we might find improvement from learning multiple models corresponding to different speaking styles.
One of the challenges that all accelerators face, is to execute loops that have if-then-else constructs. There are three ways to accelerate loops with an if-then-else construct on a Coarse-grained reconfigurable archi...
详细信息
ISBN:
(纸本)9781479930173
One of the challenges that all accelerators face, is to execute loops that have if-then-else constructs. There are three ways to accelerate loops with an if-then-else construct on a Coarse-grained reconfigurable architecture (CGRA): full predication, partial predication, and dual-issue scheme. In comparison with the other schemes, dual-issue scheme may achieve the best performance, but it requires compiler support - which does not exist. In this paper, we develop compiler techniques to map loops with conditionals on CGRA for the dual-issue scheme. Our experiments show: i) 40% of loops that can be accelerated on CGRA have conditionals, ii) The proposed dual-issue scheme enables our compiler to accelerate loops 40% faster than full predication scheme proposed in [12], and iii) Our compiler assisted dual issue scheme can exploit richer interconnects, if present. Copyright 2014 ACM.
Teachable agents foster student learning by employing the learning by teaching paradigm. Since social factors influence learning from this paradigm, understanding which social behaviors a teachable agent should embody...
详细信息
In recent years, Operations Research/Management (OR/OM) has had a significant impact on improving the performance of hospital Emergency Departments (EDs). This includes improving a wide range of processes involving pa...
详细信息
We present a 3D indoor positioning system with foot mounted low cost MEMS sensors. The sensors includes the accelerometers, gyroscopes, and barometer. The output of accelerometers and gyroscopes are used to calculate ...
详细信息
ISBN:
(纸本)9781479982622
We present a 3D indoor positioning system with foot mounted low cost MEMS sensors. The sensors includes the accelerometers, gyroscopes, and barometer. The output of accelerometers and gyroscopes are used to calculate the zero velocity update (ZUPT) and the movement of one step. The barometer is used to detect the altitude changes. A Kalman filter based framework is used to fusion the outputs of the sensors and estimate the non-linear errors of the position and heading, which increased over time. A particle filter is used to further reduce the errors. The test result shows that the designed system perform well.
When data are large and query processing workloads consist of data selection and aggregation operations (as in online analytical processing), column-oriented data stores are generally the preferred choice of data orga...
详细信息
ISBN:
(纸本)9783893180653
When data are large and query processing workloads consist of data selection and aggregation operations (as in online analytical processing), column-oriented data stores are generally the preferred choice of data organization, because they enable effective data compression, leading to significantly reduced IO. Most columnstore architectures leverage bitmap indices, which themselves can be compressed, for answering queries over data columns. Columndomains (e.g., geographical data, categorical data, biological taxonomies, organizational data) are hierarchical in nature, and it may be more advantageous to create hierarchical bitmap indices, that can help answer queries over different sub-ranges of the domain. However, given a query workload, it is critical to choose the appropriate subset of bitmap indices from the given hierarchy. Thus, in this paper, we introduce the cut-selection problem, which aims to help identify a subset (cut) of the nodes of the domain hierarchy, with the appropriate bitmap indices. We discuss inclusive, exclusive, and hybrid strategies for cut-selection and show that the hybrid strategy can be efficiently computed and returns optimal (in terms of IO) results in cases where there are no memory constraints. We also show that when there is a memory availability constraint, the cut-selection problem becomes difficult and, thus, present efficient cut-selection strategies that return close to optimal results, especially in situations where the memory limitations are very strict (i.e., the data and the hierarchy are much larger than the available memory). Experiment results confirm the efficiency and effectiveness of the proposed cut-selection algorithms.
This paper investigates group/team development in computer engineering courses at a University in the Central USA from the perspective of organization behavior theory, specifically Tuckman's model of the stages of...
详细信息
This paper investigates group/team development in computer engineering courses at a University in the Central USA from the perspective of organization behavior theory, specifically Tuckman's model of the stages of group development. The investigation, conducted through linguistic analysis of student reflection essays, and through focus group interviews, also presents STEM education researchers with a method to obtain nuanced information about interpersonal skills issues such as how groups and teams function. A third contribution of the paper is a review of the organizational behavior literature on teams and groups with a concern for its application to modern engineering education.
In an attempt to assist proctors to prevent test takers from academic dishonesty in remotely administrated exams, this study investigated the ability of test takers' behaviors during online assessments to predict ...
详细信息
Sub-Tenancy Architecture (STA), is an extension of Multi-Tenancy Architecture (MTA), allows tenants to offer services for subtenant developers to customize their applications in the SaaS infrastructure [1]. In a STA s...
详细信息
ISBN:
(纸本)9781479982622
Sub-Tenancy Architecture (STA), is an extension of Multi-Tenancy Architecture (MTA), allows tenants to offer services for subtenant developers to customize their applications in the SaaS infrastructure [1]. In a STA system, tenants are autonomous decentralized entities who can create subtenants, and grant their resources (including private services and data) to their subtenants. The isolation and sharing relations between parent-child tenants, sibling tenants or non-related tenants are more complicated than those between tenants in MTA. It is important to keep resource private, and at the same time, allow them to be shared, and support application customizations for tenants. This paper provides a formal definition of a new tenant-based access control model based on Administrative Role-Based Access Control (ARBAC) for STA in SaaS. Autonomous Areas (AA) and AA-tree are proposed to describe the autonomy of tenants, including their isolation and sharing relationships. Different resource sharing methods are given out to create and deploy the access control scheme in STA models.
Named Data Networking (NDN) is a novel networking approach that aims at overcoming some of the limitations of the current Internet. In particular, NDN aims at providing better privacy and security by focusing on the d...
详细信息
暂无评论