3
$\begingroup$

I'm rather new to R and statistics.

I'm analyzing intonation curves (time, fundamental frequency), and I'm interested in comparing pitch curves of different speakers. I am particularly interested in the shape and range of the curves. Do you think correlation is the way to go? Do you know of any other techniques to analyze these data?

Problem is I do not have the same number of pitch values for each speaker, and time data (total utterance length) varies, too. Is there a way -or is it even necessary- to normalize the time data?

Here's an example of the data:

Curve A
           T       F0
1 0.04035147 5.417267
2 0.09035147 5.376210
3 0.32035147 5.569663
4 0.45035147 5.354541
5 0.57035147 5.306933
6 0.78035147 5.778286
7 0.84035147 5.972072
8 1.01035147 6.054488

Curve B
         T       F0
1 0.2240249 5.222333
2 0.2740249 5.232854
3 0.3640249 5.210945
4 0.7340249 5.650391
5 0.9240249 5.845682
6 1.1040249 6.111766
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.