Table 4. Per-vowel token-level classification accuracy (LDA, leave-one-out cross-validation)

Vowel	Group	Classification accuracy (%)
/u:/	non-front	85.7
/e/	front	85.7
/i:/	front	71.4
/oʊ/	non-front	71.4
/eɪ/	front	57.1 (boundary)
/ɔ:/	non-front	57.1 (boundary)

Chance level=50%. Overall LDA accuracy (n=42 tokens)=71.4%.
LDA, linear discriminant analysis.