Characterisation of speech diversity using self-organising maps
This work addresses pronunciation analysis for Australian English speakers, but it is incremental as it builds on existing SOM-based methods with a specific dataset.
The paper tackled the problem of evaluating pronunciation diversity in Australian English using multilevel self-organizing maps (SOMs) on /hVd/ syllable utterances, achieving low phoneme error rates as a result.
We report investigations into speaker classification of larger quantities of unlabelled speech data using small sets of manually phonemically annotated speech. The Kohonen speech typewriter is a semi-supervised method comprised of self-organising maps (SOMs) that achieves low phoneme error rates. A SOM is a 2D array of cells that learn vector representations of the data based on neighbourhoods. In this paper, we report a method to evaluate pronunciation using multilevel SOMs with /hVd/ single syllable utterances for the study of vowels, for Australian pronunciation.