This is Video 16 of our series on prosody. Two instances of essentially the same prosodic behavior may yield very different measurements, due to differences in speakers, recording conditions, etc. Use of appropriate normalization techniques can enable better comparisons and aggregations over diverse data.
00:00 Compensating for Speaker Differences
01:09 Pitch Value Distributions
02:22 Subtracting Minimums
03:19 Subtracting Averages
04:22 Standard Deviations and Z-Normalization
05:36 Percentiles
06:34 Normalizing in General
07:12 Normalizing Intensity
09:09 General Cautions
