Duration prediction

[Anonymous Student]

Is duration prediction done at the segmental or suprasegmental level? is it computed using CART as classifier (using labels like) or using regression (giving duration in ms?)?

[Simon]

In Festival, and many other systems, duration is predicted at the segmental (i.e., phone) level. Festival uses a regression tree, because duration is a continuous value.

The tree could directly predict duration in ms or s. But it’s often better to predict what is called a z-score (the figure in that article is helpful). This is the duration expressed as the difference (in numbers of standard deviations) from the mean duration for that phoneme. Here’s what z-score means for duration:

large positive numbers: duration is a lot longer than average
small positive numbers: duration is bit longer than average
zero: duration is exactly equal to the average
negative numbers: duration is bit shorter than average
large negative numbers: duration is lot shorter than average

and we would expect z-scores in a relatively narrow range about the mean (+/- 2 would cover 96% of all cases).

[Author]

Posts