Kate Hone's Speech Research Page

Usable speech interactive technology

I am involved in research which explores the human factors implications of using speech technology in user interfaces.  Speech recognition technology differs from most other input devices because of its error prone nature and this has important implications for the design of systems.  Summaries of key research areas are provided below.

Current Projects:
The Millennium Homes Project

This DTI/ EPSRC funded project, led by the Brunel Institute for Biotechnology at Brunel with Prof. Heinz Wolff, is developing interfaces for houses to support the quality of life of independent-living frail and elderly people. As part of this we are carrying out research into the use of speech interfaces by older users. [Research assistant: Lorna Lines]

Subjective Assessment of Speech System Interfaces (SASSI)

I am currently working on the development of a measure for the subjective assessment of speech system interfaces.  An initial version of the questionnaire has been piloted in the Dialogue Constraints Project (see below) and in the Speech Ideas (SPEECH Interfaces for DrivEr informAtion Systems) research program at Loughborough.  Further research is planned in order to produce a fully validated version of the questionnaire. Click here for more information.

Past Projects:
Dialogue Constraints Project (October 1997-September 1998)

This EPSRC funded project investigated the impact of dialogue constraints on both automatic speech recogniser performance and human behaviour.  A key conclusion from the research is that human behaviour with highly constrained dialogues is predictable enough to allow the development of models of human and system behaviour which can be used in the early stages of design.  Engineering models of this kind have the potential to produce savings in development time for new speech dialogues and to allow the development of faster human-computer interactions. However, human behaviour is much less predictable when the constraint in the dialogue is implied rather than explicit.  Further research is needed before the problem of modelling human responses with these dialogues will be tractable.  The final report provides details of the main experimental findings, the key implications for design and suggests some further research which could be performed in order to build upon the current work and fully realise its value.
[EPSRC grant reference GR/L94710]

Speech and Problem Solving Project (with David Golightly)

This project was funded by the School of Computer Science and Information Technology at Nottingham University and investigated the effect of using speech input on problem solving behaviour using the 8-puzzle.  The results showed that speech interaction can influence display-based problem solving, with users taking fewer steps to problem solution with speech input than with direct manipulation.  Examination of the pattern of results obtained suggests that this effect may be due to the processing delay inherent in current speech recognition technology.  Further theoretical research is needed to test this hypothesis.  Another potential avenue for future research is looking at the effect of speech input in more realistic problem solving tasks.

[Kate Hone's Home Page]

Last updated 5/3/02