Appendix A
Additional Problems
The problems in this document may
be used as extra review or practice for quizzes and exams. They are
organized by chapter and are very similar in spirit to those found in the
text. When referring to problems in this document, we will use the chapter
number followed by the problem number. For example, Problem 1.3 refers to
the third problem in the problem set for Chapter 1. The answers to these
problems may be found in a companion document at this website.
Problems for Chapter 9
-
Brown-headed cowbirds, Molothrus ater, are
brood parasites; they lay their eggs in the nests of other birds. To do
so, they must locate suitable host nests. Two behaviors cowbirds might use
as cues are activity and aggression of nest owners, which may indicate
that there is an active nest in the area. To test this idea, 17 nests of
clay-colored sparrows were located in a marsh area. A female cowbird model
was placed for a five-minute time interval at each of three distances, 0.5
m, 2.5 m, and 4.5 m, from the nests to determine at what distance
clay-colored sparrows reacted to a cowbird. A fifteen-minute rest interval
was used before relocating the model to the next distance. The ordering of
the distances was chosen randomly for each nest. The number of 10-second
intervals in which the sparrow "chipped" over the five- minute interval was
recorded for each model placement. For a given nest, each of the three
distances was ranked from 1 to 3 corresponding to the number of time
intervals in which chipping occurred. Using the data presented below,
determine whether there was a difference in the chipping rate among the
three distances at which the models were placed. If so, determine which
pairs of distances produce the different chipping rates. (Based on
concepts reported in Paula Grieef, "Cues used by brood parasites and
predators to locate nests", 9. University of
Mannitoba Field Station ( Delta Marsh) Annual Reports ,1994, 29: 71 82. See also www.umanitoba.ca/faculties/science/delta
marsh/reports/1994/grieef/grieef.html .)
| Distance |
0.5 m |
1.5 m |
4.5 m |
| Rank sum Rj |
43 |
35 |
24 |
- With the
advent of computerized speech recognition, automatic speaker recognition
has become a problem of interest. Automatic speaker recognition (SR) is
comprised of speaker identification (SI) and speaker verification (SV). SV
is the process of verifying whether a speaker is who he claims to be by
using a given recorded speech, whereas SI is the determination of the
identity of the person most likely to have spoken a given passage (from
among a known population). In a recent study, a model reflecting 40
acoustic features of speech were extracted from tape recordings of each of
14 males. Subsequently, six different methods (CBD: City block distance;
ED: Euclidean distance; WED: Weighted Euclidean distance; MD: Mahalanobis
distance; GP: Gaussian probability density estimation; and KLT:
probability estimation after Karhunen-Loeve transformation) were used to
compare the reference models to new test recordings of these same 14
males. For each speaker the number of matches (out of 40) is listed below
for each of the six methods. The researchers used the Friedman test to
determine whether there were differences in accuracy among the methods.
What did they find? Use paired comparisons, if appropriate. (Based on data
reported in Sherman Ong and Cheng-Hong Yang, A comparative study of
text-independent speaker identification using statistical features,
International Journal of Computer Engineering and Management, 1998, 6 (1)
. Also see www.journal.au.edu/ijcem/jan98/article5.html)
| Method |
|
|
|
|
|
|
| Speaker |
CBD |
ED |
WED |
MD |
GP |
KLT |
| 1 |
37 |
33 |
38 |
35 |
34 |
38 |
| 2 |
39 |
39 |
40 |
40 |
40 |
40 |
| 3 |
33 |
26 |
35 |
39 |
29 |
35 |
| 4 |
33 |
26 |
39 |
37 |
38 |
38 |
| 5 |
38 |
37 |
40 |
37 |
38 |
39 |
| 6 |
28 |
31 |
33 |
36 |
35 |
36 |
| 7 |
36 |
37 |
37 |
39 |
39 |
38 |
| 8 |
30 |
24 |
33 |
36 |
36 |
38 |
| 9 |
39 |
38 |
40 |
33 |
33 |
38 |
| 10 |
32 |
32 |
34 |
38 |
38 |
39 |
| 11 |
28 |
26 |
27 |
32 |
33 |
33 |
| 12 |
27 |
23 |
29 |
39 |
39 |
37 |
| 13 |
39 |
39 |
39 |
39 |
40 |
39 |
| 14 |
40 |
40 |
40 |
40 |
40 |
40 |
|
