PLDA based speaker recognition on short utterances

This paper investigates the effects of limited speech data in the context of speaker verification using a probabilistic linear discriminant analysis (PLDA) approach. Being able to reduce the length of required speech data is important to the development of automatic speaker verification system in real world applications. When sufficient speech is available, previous research has shown that heavy-tailed PLDA (HTPLDA) modeling of speakers in the i-vector space provides state-of-the-art performance, however, the robustness of HTPLDA to the limited speech resources in development, enrolment and verification is an important issue that has not yet been investigated. In this paper, we analyze the speaker verification performance with regards to the duration of utterances used for both speaker evaluation (enrolment and verification) and score normalization and PLDA modeling during development. Two different approaches to total-variability representation are analyzed within the PLDA approach to show improved performance in short-utterance mismatched evaluation conditions and conditions for which insufficient speech resources are available for adequate system development. The results presented within this paper using the NIST 2008 Speaker Recognition Evaluation dataset suggest that the HTPLDA system can continue to achieve better performance than Gaussian PLDA (GPLDA) as evaluation utterance lengths are decreased. We also highlight the importance of matching durations for score normalization and PLDA modeling to the expected evaluation conditions. Finally, we found that a pooled total-variability approach to PLDA modeling can achieve better performance than the traditional concatenated total-variability approach for short utterances in mismatched evaluation conditions and conditions for which insufficient speech resources are available for adequate system development.

Knowledge-Intensive Business Processes: Proceedings of the 1st International Workshop on Knowledge-intensive Business Processes [CEUR Workshop Proceedings, Volume 861]

Nowadays, Workflow Management Systems (WfMSs) and, more generally, Process Management Systems (PMPs) are process-aware Information Systems (PAISs), are widely used to support many human organizational activities, ranging from well-understood, relatively stable and structures processes (supply chain management, postal delivery tracking, etc.) to processes that are more complicated, less structured and may exhibit a high degree of variation (health-care, emergency management, etc.). Every aspect of a business process involves a certain amount of knowledge which may be complex depending on the domain of interest. The adequate representation of this knowledge is determined by the modeling language used. Some processes behave in a way that is well understood, predictable and repeatable: the tasks are clearly delineated and the control flow is straightforward. Recent discussions, however, illustrate the increasing demand for solutions for knowledge-intensive processes, where these characteristics are less applicable. The actors involved in the conduct of a knowledge-intensive process have to deal with a high degree of uncertainty. Tasks may be hard to perform and the order in which they need to be performed may be highly variable. Modeling knowledge-intensive processes can be complex as it may be hard to capture at design-time what knowledge is available at run-time. In realistic environments, for example, actors lack important knowledge at execution time or this knowledge can become obsolete as the process progresses. Even if each actor (at some point) has perfect knowledge of the world, it may not be certain of its beliefs at later points in time, since tasks by other actors may change the world without those changes being perceived. Typically, a knowledge-intensive process cannot be adequately modeled by classical, state of the art process/workflow modeling approaches. In some respect there is a lack of maturity when it comes to capturing the semantic aspects involved, both in terms of reasoning about them. The main focus of the 1st International Workshop on Knowledge-intensive Business processes (KiBP 2012) was investigating how techniques from different fields, such as Artificial Intelligence (AI), Knowledge Representation (KR), Business Process Management (BPM), Service Oriented Computing (SOC), etc., can be combined with the aim of improving the modeling and the enactment phases of a knowledge-intensive process. The 1st International Workshop on Knowledge-intensive Business process (KiBP 2012) was held as part of the program of the 2012 Knowledge Representation & Reasoning International Conference (KR 2012) in Rome, Italy, in June 2012. The workshop was hosted by the Dipartimento di Ingegneria Informatica, Automatica e Gestionale Antonio Ruberti of Sapienza Universita di Roma, with financial support of the University, through grant 2010-C26A107CN9 TESTMED, and the EU Commission through the projects FP7-25888 Greener Buildings and FP7-257899 Smart Vortex. This volume contains the 5 papers accepted and presented at the workshop. Each paper was reviewed by three members of the internationally renowned Program Committee. In addition, a further paper was invted for inclusion in the workshop proceedings and for presentation at the workshop. There were two keynote talks, one by Marlon Dumas (Institute of Computer Science, University of Tartu, Estonia) on "Integrated Data and Process Management: Finally?" and the other by Yves Lesperance (Department of Computer Science and Engineering, York University, Canada) on "A Logic-Based Approach to Business Processes Customization" completed the scientific program. We would like to thank all the Program Committee members for the valuable work in selecting the papers, Andrea Marrella for his valuable work as publication and publicity chair of the workshop, and Carola Aiello and the consulting agency Consulta Umbria for the organization of this successful event.

A unified description language for human to automated services

Through the rise of cloud computing, on-demand applications, and business networks, services are increasingly being exposed and delivered on the Internet and through mobile communications. So far, services have mainly been described through technical interface descriptions. The description of business details, such as pricing, service-level, or licensing, has been neglected and is therefore hard to automatically process by service consumers. Also, third-party intermediaries, such as brokers, cloud providers, or channel partners, are interested in the business details in order to extend services and their delivery and, thus, further monetize services. In this paper, the constructivist design of the UnifiedServiceDescriptionLanguage (USDL), aimed at describing services across the human-to-automation continuum, is presented. The proposal of USDL follows well-defined requirements which are expressed against a common service discourse and synthesized from currently available servicedescription efforts. USDL's concepts and modules are evaluated for their support of the different requirements and use cases.

The relationship between listening and other language skills in International English Language Testing System

Listening comprehension is the primary channel of learning a language. Yet of the four dominant macro-skills (listening, speaking, reading and writing), it is often difficult and inaccessible for second and foreign language learners due to its implicit process. The secondary skill, speaking, proceeds listening cognitively. Aural/oral skills precede the graphic skills, such as reading and writing, as they form the circle of language learning process. However, despite the significant relationship with other language skills, listening comprehension is treated lightly in the applied linguistics research. Half of our daily conversation and three quarters of classroom interaction are virtually devoted to listening comprehension. To examine the relationship of listening skill with other language skills, the outcome of 1800 Iranian participants undertaking International English Language Testing System (IELTS) in Tehran indicates the close correlation between listening comprehension and the overall language proficiency.

Enhancing foreign language learning through listening strategy delivered in L1: an experimental study

Listening used in language teaching refers to a complex process that allows us to understand spoken language. The current study, conducted in Iran with an experimental design, investigated the effectiveness of teaching listening strategies delivered in L1 (Persian) and its effect on listening comprehension in L2. Five listening strategies: Guessing, making inferences, identifying topics, repetition, and note-taking were taught over 14 weeks during a semester. Sixty lower intermediate female participants came from two EFL classrooms in an English language institute. The experimental class (n = 30) who listened to their classroom activities performed better (t value = 10.083) than the control class using a methodology that led learners through five listening strategies in Persian. The same teacher taught the students in the control class (n = 30), who listened to the same classroom listening activities without any of the above listening strategies. A pre and post listening test made by a group of experts in the language institute assessed the effect of teaching listening strategies delivered in L1. Results gathered on the post intervention listening test revealed that listening strategies delivered in L1 led to a statistically significant improvement in their discrete listening scores compared with the control group.

Is language a barrier for quality care in hospitals? A case series from an Emergency Department of a teaching hospital in Brisbane

Aim: The aim of this pilot study is to describe the use of an Emergency Department (ED) at a large metropolitan teaching hospital by patients who speak English or other languages at home. Methods: All data were retrieved from the Emergency Department Information System (EDIS) of this tertiary teaching hospital in Brisbane. Patients were divided into two groups based on the language spoken at home: patients who speak English only at home (SEO) and patients who do not speak English only or speak other language at home (NSEO). Modes of arrival, length of ED stay and the proportion of hospital admission were compared among the two groups of patients by using SPSS V18 software. Results: A total of 69,494 patients visited this hospital ED in 2009 with 67,727 (97.5%) being in the SEO group and 1,281 (1.80%) in the NSEO group. The proportion of ambulance utilisation in arrival mode was significantly higher among SEO 23,172 (34.2%) than NSEO 397 (31.0%), p <0.05. The NSEO patients had longer length of stay in the ED (M = 337.21, SD = 285.9) compared to SEO patients (M= 290.9, SD = 266.8), with 46.3 minutes (95%CI 62.1, 30.5, p <0.001) difference. The admission to the hospital among NSEO was 402 (31.9%) higher than SEO 17,652 (26.6%), p <0.001. Conclusion: The lower utilisation rates of ambulance services, longer length of ED stay and higher hospital admission rates in NSEO patients compared to SEO patients are consistent with other international studies and may be due to the language barriers.

Metacognitive strategy instruction in English as Foreign Language (EFL) listening skill

Listening skill is a critical part of language learning in general, and second, and foreign language learning, in particular. However, the process of this basic skill has been overlooked compared to other skills such as speaking, reading and writing, in terms of an explicit instruction, and the product of listening is instead mainly tested indirectly through comprehension questions in classrooms. Instruction of metacognitive strategies demonstrates the pivotal impact on second language listening skill development. In this vein, this study used a mixed method with an experimental male group (N = 30) listened to texts using process-approach pedagogy directed students through metacognitive strategies over a semester (10 weeks) in Iran. To investigate the impact of metacognitive strategy instruction, the following approaches were implemented. First, IELTS listening test was used to track any development of listening comprehension. Second, using Vandergrift et al. (2006) Metacognitive Awareness Listening Questionnaire (MALQ) helped examine students’ use of metacognitive strategies in listening comprehension. Finally, interviews were used to examine students’ use of strategies in listening. The results showed that students had a development in comprehension of IELTS listening test, but no statistical significant development of metacognitive awareness in listening was demonstrated. Students and teacher reported in the interviews students used multiple strategies to approach listening comprehension besides metacognitive strategies.

Instructing foreign language learners how to listen through metacognitive strategies : an empirical study

This study uses a mixed method approach to investigate the impact of metacognitive strategies instruction on listening comprehension. An experimental group (N = 30) of university students are guided through a process-approach pedagogy over one semester (10 weeks) in Iran. IELTS listening tests are used to track development of listening comprehension in participants who are then asked to complete a Metacognitive Awareness Listening Questionnaire (MALQ). The questionnaire examines students’ employment of metacognitive strategies in listening comprehension. Finally, interviews are used to explore students’ use of strategies in listening. Results indicate that participants develop listening comprehension, but no metacognitive awareness in listening. Students reported in the interviews that they use multiple strategies (cognitive and metacognitive) to approach listening comprehension.

The impact of English as a Foreign Language (EFL) listening comprehension through first language (L1) listening strategy training

Listening is the basic and complementary skill in second language learning. The term listening is used in language teaching to refer to a complex process that allows us to understand spoken language. Listening, the most widely used language skill, is often used in conjunction with the other skills of speaking, reading and writing. Listening is not only a skill area in primary language performance (L1), but is also a critical means of acquiring a second language (L2). Listening is the channel in which we process language in real time – employing pacing, units of encoding and decoding (the 2 processes are central to interpretation and meaning making) and pausing (allows for reflection) that are unique to spoken language. Despite the wide range of areas investigated in listening strategies during training, there is a lack of research looking specifically at how effectively L1 listening strategy training may transfer to L2. To investigate the development of any such transfer patterns the instructional design and implementation of listening strategy of L1 will be critical.

Multimodal and monomodal discourses of marketization in higher education : power, ideology, and the absence of the image

The ubiquity of multimodality in hypermedia environments is undeniable. Bezemer and Kress (2008) have argued that writing has been displaced by image as the central mode for representation. Given the current technical affordances of digital technology and user-friendly interfaces that enable the ease of multimodal design, the conspicuous absence of images in certain domains of cyberspace is deserving of critical analysis. In this presentation, I examine the politics of discourses implicit within hypertextual spaces, drawing textual examples from a higher education website. I critically examine the role of writing and other modes of production used in what Fairclough (1993) refers to as discourses of marketisation in higher education, tracing four pervasive discourses of teaching and learning in the current economy: i) materialization, ii) personalization, iii) technologisation, and iv) commodification (Fairclough, 1999). Each of these arguments is supported by the critical analysis of multimodal texts. The first is a podcast highlighting the new architectonic features of a university learning space. The second is a podcast and transcript of a university Open Day interview with prospective students. The third is a time-lapse video showing the construction of a new science and engineering precinct. These three multimodal texts contrast a final web-based text that exhibits a predominance of writing and the powerful absence or silencing of the image. I connect the weightiness of words and the function of monomodality in the commodification of discourses, and its resistance to the multimodal affordances of web-based technologies, and how this is used to establish particular sets of subject positions and ideologies through which readers are constrained to occupy. Applying principles of critical language study by theorists that include Fairclough, Kress, Lemke, and others whose semiotic analysis of texts focuses on the connections between language, power, and ideology, I demonstrate how the denial of image and the privileging of written words in the multimodality of cyberspace is an ideological effect to accentuate the dominance of the institution.

A world map of knowledge in the making : Wikipedia's Inter-Language Linkage as a dependency explorer of global knowledge accumulation

Analysis of Wikipedia's inter-language links provides insight into a new mechanism of knowledge sharing and linking worldwide.