Lab 9 Generative Synthesis
docx
School
California State University, Fullerton *
*We aren’t endorsed by this school
Course
285
Subject
Linguistics
Date
Dec 6, 2023
Type
docx
Pages
3
Uploaded by happykorgirl
Name: ________________________________________________________________________
Discussion section time: __________________________________________________________
Linguistics 285: Lab 9
Goals:
-
Practice dynamic programming
-
Calculate tone values using Generative Synthesis
Part1: Generative Synthesis
You are creating a synthesis for the following word: “hide” [hɑid].
11. A generative synthesis would recreate this word moment by moment.
Using the formants
drawn on this spectrogram as a guide to which tones are the most prominent in the natural
production of “hide,” which 5 tones would a generative synthesis program use to recreate
this word?
Notice that we’re using a sampling rate of 100 ms.
Lowest Tone
Tone 2
Tone 3
Tone 4
Highest Tone
300 ms
900
1100
2100
3400
4800
400 ms
950
1050
2100
3400
4800
500 ms
600 ms
700 ms
800 ms
900 ms
12. How many data points do you have for the phoneme /h/?
For /ɑ/?
Is Generative Synthesis
sensitive to phoneme boundaries?
13. The word above is about 1 second long.
It is not uncommon that a Generative Synthesis
program would take 16,000 samples each second.
Given that the human production has 40
harmonics at any given moment, how many tones would be used to synthesize this word?
14. There are three ways to improve the synthesis you outlined in (17).
Can you name all three?
a.
b.
c.
15. What if you wanted to synthesis the word “dye” [dɑi] instead using generative synthesis.
What would you have to do?
16. What would you have to do if you wanted to synthesize the word “hide” in a Chicago dialect
instead of a Southern California dialect?
17. What would you have to do if you wanted to synthesize the word “hide” in a question
instead of in a statement?
Part2: Machine Learning
18. Open Praat and record yourself saying the following words: “seek” /sik/ and “sick” /sɪk/.
What are your F2 values for these two words?
Word
F2
Seek
Sick
19. The words you recorded above represent a data set. A speaker produces a word with an F2
of 2400 Hz.
Based on your data set from (24), is the word produced “Tim” /tɪm/ or
“team” /tim/?
In other words, is 2400 Hz the F2 of an /i/ or of an /ɪ/?
How certain are you?
20. The class will share their F2 values for (24).
This creates a larger data set.
What is the
highest and lowest value for the two vowels in your combined data set?
What is the
average?
Word
Highest F2
Lowest F2
Average F2
Seek
Sick
21. Now, using your better dataset from (26), is a word produced with an F2 of 2400 Hz the
word “Tim” or “team”?
How certain are you?
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
- Access to all documents
- Unlimited textbook solutions
- 24/7 expert homework help