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…

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…

Corpora creation

In an earlier blog post, iTalk2Learn partner, Sail, talked about the statistical nature of the two models which are employed for automatic speech recognition: The acoustic model The language model These models need to be trained on a so-called ‘corpus’ before they can be used in the recognition process. In this blog post, we’ll hear more from Sail…

Exercise from Year 6 - Percentages

Collecting voice recordings from Whizzers in London

iTalk2Learn has opened our eyes to new possibilities by highlighting the influence of emotion and speech in students’ learning. One of core differentiators at Whizz Education (Whizz) is the ability to engage students in the learning process using diverse, interactive content. The ability to detect and respond to students’ affective states will make the Whizz platform…