1992 Working Papers

Recent Submissions

Now showing 1 - 5 of 8
  • Item
    Comparing human and computational models of music prediction
    (Working Paper, Department of Computer Science, University of Waikato, 1992) Witten, Ian H.; Manzara, Leonard C.; Conklin, Derrell
    The information content of each successive note in a piece of music is not an intrinsic musical property but depends on the listener's own model of a genre of music. Human listeners' models can be elicited by having them guess successive notes and assign probabilities to their guesses by gambling. Computational models can be constructed by developing a structural framework for prediction, and "training" the system by having it assimilate a corpus of sample compositions and adjust its internal probability estimates accordingly. These two modeling techniques turn out to yield remarkably similar values for the information content, or "entropy," of the Bach chorale melodies. While previous research has concentrated on the overall information content of whole pieces of music, the present study evaluates and compares the two kinds of model in fine detail. Their predictions for two particular chorale melodies are analyzed on a note-by-note basis, and the smoothed information profiles of the chorales are examined and compared. Apart from the intrinsic interest of comparing human with computational models of music, several conclusions are drawn for the improvement of computational models.
  • Item
    Data logging and performance analysis software for teachers of indigenous New Zealanders: early results
    (Working Paper, Department of Computer Science, University of Waikato, 1992) Barbour, Robert H.; Ford, Greg; Cunningham, Sally Jo
    Technology, in the form of personal computers, is making inroads into everyday life in every part of every nation. It is frequently assumed that this is 'a good thing'. However, there is a need for the people in each cultural group in each nation to appropriate technology for themselves. Indigenous people, such as the Maori of New Zealand/Aotearoa, are in danger of losing their language because technology has a European face. Yet despite the fact that the Maori are currently experiencing a cultural renaissance, there are no commercially available products that are specifically designed for Maori-speaking people.
  • Item
    Natural language processing in speech understanding systems
    (Working Paper, Department of Computer Science, University of Waikato, 1992) Holmes, Geoffrey
    Speech understanding systems (SUS's) came of age in late 1971 as a result of a five year development programme instigated by the Information Processing Technology Office of the Advanced Research Projects Agency (ARPA) of the Department of Defense in the United States. The aim of the programme was to research and develop practical man-machine communication systems. It has been argued since, that the main contribution of this project was not in the development of speech science, but in the development of artificial intelligence. That debate is beyond the scope of this paper, though no one would question the fact that the field to benefit most within artificial intelligence as a result of this programme is natural language understanding. More recent projects of a similar nature, such as projects in the United Kingdom's ALVEY programme and Europe's ESPRIT programme have added further developments to this important field. This paper presents a review of some of the natural language processing techniques used within speech understanding systems. In particular, techniques for handling syntactic, semantic and pragmatic information are discussed. They are integrated into SUS's as knowledge sources. The most common application of these systems is to provide an interface to a database. The system has to perform a dialogue with a user who is generally unknown to the system. Typical examples are train and aeroplane timetable enquiry systems, travel management systems and document retrieval systems.
  • Item
    Getting research students started: a tale of two courses
    (Working Paper, Department of Computer Science, University of Waikato, 1992) Witten, Ian H.; Bell, Timothy C.
    As graduate programs in Computer Science grow and mature and undergraduate populations stabilize, an increasing proportion of our resources is being devoted to the training of researchers in the field. Many inefficiencies are evident in our graduate programs. These include undesirably long average times to thesis completion, students' poor work habits and general lack of professionalism, and the unnecessary duplication of having supervisors introduce their students individually to the basics of research. Solving these problems requires specifically targeted education to get students started in their graduate research and introduce them to the skills and tools needed to complete it efficiently and effectively. We have used two different approaches in our respective departments. One is a (half-) credit course on research skills; the other a one-week intensive non-credit "survival course" at the beginning of the year. The advantage of the former is the opportunity to cover material in depth and for students to practice their skills; the latter is much less demanding on students and is easier to fit into an existing graduate program.
  • Item
    Voice input and information exchange in asynchronous group communication
    (Working Paper, Department of Computer Science, University of Waikato, 1992) McQueen, Robert J.
    Existing computer supported co-operative work (CSCW) systems for group communication typically require some amount of keyboard input, and this may limit their usefulness. A voice input prototype system for asynchronous (time separated transactions) group communication (AGC) with simulated conversion to text was developed and an experiment constructed to investigate if advantages over conventional keyboard input computer conferencing were possible for the information exchange task. Increases in words used and facts disclosed were higher for voice input compared to text input, which implies that voice input capability could be advantageous for future asynchronous group communication systems supporting information exchange.