Confidence intervals for forced alignment with the Mason-Alberta Phonetic Segmenter

Forced alignment is a common tool in experimental phonetics to align audio with orthographic and phonetic transcriptions. Phonetic segmentation is not a straightforward process, however, and boundaries between phonetic segments cannot be easily determined. Most forced alignment tools provide a single estimate of a boundary based on conditional probabilities of segment categories given some acoustic data. The present project introduces a method of deriving confidence intervals for these boundaries using a neural network ensemble technique with the Mason-Alberta Phonetic Segmenter. Ten different segment classifier neural networks were previously trained, and the alignment process is repeated with each model. The alignment ensemble is then used to place the boundary at the median of the time points, and 97.85% confidence intervals are constructed using order statistics. On the Buckeye and TIMIT corpora, the ensemble boundaries show a slight improvement over using just a single model. The confidence intervals are incorporated into Praat TextGrids using a point tier, and they are also output as a table for researchers to analyze separately.