Tone realisation in a Yoruba speech recognition corpus

Abstract

The authors investigate the acoustic realisation of tone in short continuous utterances in Yoruba. Fundamental frequency contours are extracted for automatically aligned syllables from a speech corpus of 33 speakers collected for speech recognition development. Extracted contours are processed and analysed statistically to describe acoustic properties in different tonal contexts. The authors demonstrate how features useful for tone recognition or synthesis can be successfully extracted from a corpus of this nature and confirm some previously described phenomena in this context.