Thursday, March 19, 1998 at 13:10:12
I currently have an honours student researching into the value of filled pause analysis as a tool in forensic speaker identification. This is how we came across your web page. I do a fair amount of forensic work, and I find that filled pauses are a good indicator of speaker ID, but a lot more research is needed to evaluate the validity of this measure.
I had never considered applications of filled pause research for forensic work, but I did find in my study that speakers are highly individualistic in their patterns of hesitation. However, the degree to which the use of patterns are consistent, as well as the complexity of the patterns, and the malleability of an individual's patterns make me wonder how it could be a reliable identifier.
This site is
maintained by Ralph L. Rose