About the project

In this project we investigated variation in English intonation, insofar as it is represented in an existing corpus (the IViE corpus) containing recordings of nine dialects of English.

Whereas prior models of intonation focus on a single dialect and style, we have constructed a statistical computational model of intonation which takes account of variation due to dialect, speaking style, gender and individual speaker habits.

The model will be useful for the UK speech technology industry. Developers of automatic speech synthesis and recognition systems require linguistically rich yet quantitative models of intonation because current systems cannot produce or recognise the intonation patterns of different English dialects, styles or speakers.Our work will also be valuable for speech therapists, for whom we have prepared an informative leaflet, and for English language teachers. Examples of the most common tunes illustrated in the leaflet can be heard here.

Principal Investigators: Dr Esther Grabe and Dr John Coleman
Associated Research Fellow: Dr Greg Kochanski