Standing on the shoulders of giants

In his recent book Teaching Machines, Bill Ferster charts the fascinating history of educational technology, from the humble origins of the postal Correspondence Courses for miners in the 19th Century through to the virtual tutors of the present day. As part of his analysis the author observes a shift in emphasis not only in the…

Evaluating the performance of automatic speech recognition systems

iTalk2Learn partners, Sail, explain how they evaluate automatic speech recognition systems Word Error Rate The standard measurement to assess the performance of an automatic speech recognition (ASR) system is the so-called word-error-rate (WER, (Jelinek, 1997)). WER is a minimum edit-distance measure produced by applying a dynamic alignment between the output of the ASR system and…

Why is children’s Automatic Speech Recognition special?

Conventional speech recognition systems are failing As previous research has shown, there are many differences between the speech of an adult and that of a child – both acoustically and linguistically. That is why conventional speech recognition systems modelled on adult data are failing to perform satisfactorily on children’s speech input. Speaking isn’t straightforward Human…

iTalk2Learn intelligence platform

What is behind iTalk2Learn intelligence?

The aim of WP2 is to provide the iTalk2learn platform with intelligence that can guide students to maths mastery. But how can we make a machine intelligent? In order to answer the question, ‘how can we make a machine intelligent?’, we must first divide the problem into sub-problems. In the iTalk2Learn project, each sub-problem corresponds to a different component of the…

Intuitive Interaction Interfaces for Elementary Mathematics

Intuitive Interaction Interfaces for Elementary Mathematics Objectives, achievements and challenges Work Package 3 has a rather ambitious objective: The design and development of innovative and intuitive interaction interfaces for Elementary Mathematics, including voice and direct manipulation user interfaces. The achievement of this objective results through the following steps: Provision of speech production and voice recognition…