Page 69 - Winter Issue 2018
P. 69

I.  ., 
El .-.   += »'= :-gar-1-.‘~-.«. I F I  ‘:1
 _.' ; fig-‘*«:f%r“" 2.-;r‘.=‘s*§ix'»-'-,‘*_‘:‘-:’:v,*;5xs .*  ,-A s '
 s’ . “; ,,.,,, ..!E'5z,5Lfi-‘Q :11‘ T‘ ow
Those eligible for the ASA cash prize awards were chosen by ; ..;__  j ’, ’ “ j-7-:5   f or ._;;T if  1 1' I if
the three ASA judges from the Intel ISEF finalists. They first I   V’; 5-        L -r 
searched through the 1,800 titles and abstracts for acoustics ; ‘ff: '- “"’   3, *1: _:‘f or   f‘ L
relevance (defined in the broadest sense). The relevant proj- ;  I * _ -1 E» )3“ la‘  g ‘  I P N)‘  i
ects were then reviewed and cut to the 35 top projects that I "L  _ at ,  5 .—_- jii; ii -*
had acoustics as a primary focus of the research. Most, if not . 5, '  " ‘ ‘(T T’ [7 f _, , , _
. = «w  ...;««is'=-*«~
all, of the 13 technical areas of ASA were represented. is‘ _g 5% up *‘ — '-
The ASA judges then met and discussed the 35 projects, and ‘ vi  .
each judge chose to be a primary or secondary judge for var- '
ions Projecm Next, the Pmnary and Secondary judges Pre_ Figure 1. .Poster session at the Intel International Science and
judged the projects by reading the student’s poster boards Engmeenng Fm’-
(see Figure 1), documentation, and lab notebooks in the
absence of the student. From there, the judges selected 20 also received the Intel ISEF Best of Robotics and Intelligence
projects for student interviews. A total of five semifinalists Category Second Place Award.
Wer,e selectid Ezgiéméerviewed once or twice more by the The second place ASA winner was Sharmi Shah, an 11th
emlre Pane 0 Ju geS' grader from Colonia High School, Colonia, NI, mentored
After much deliberation, first, second, and third place final- by teacher James Danch (Physics and Astronomy Category).
ists were chosen and received cash prizes for themselves, Ms. Shah’s project was “Speech Intelligibility Analysis of
their schools, and their mentors. The first place winner re- Sound-Modulated Laser Signal Countermeasures.” It is well
ceived $1,500 plus $200 for the school and $500 for the men- established that laser light can be used as a spying device
tor. The second place finalist received $1,000 plus $100 for by measuring the modulation of the reflected light from a
the school and $250 for the mentor. The third place finalist window. Ms. Shah investigated two coatings for their ability
received $600 plus $150 cash prize for the mentor. An hon- to diffuse the laser light and prevent eavesdropping while
orable mention certificate was also awarded. Additionally, maintaining optical clarity. She evaluated the two coatings
the student winners have been invited to attend the upcom- plus a control by using speech— recognition software to ana-
ing ASA annual meeting in Victoria, BC, Canada. For pho— lyze speech recorded by the laser. Silica nanoparticle-epoxy
tos of this and past Special Award Ceremonies, see the Intel residue reduced intelligibility of the chosen speech by 47%
ISEF ASA Flickr album at while nanoparticle-dimethylsiloxane fully precluded speech
The first place ASA winner was Anwesha Mukherjee (Ro- intelligibility by the algorithjns Although the coatings lap’
botics and Intelligent Machines Category). Ms. Mukherjee §e"’fl°1d tmnsplaregt’ trangmlssuin spzcga ‘Sea: miasrired
is a 10th grader at Westview High School, Portland, OR. She or e Fofltro an mate _samP s5 an mm at t_ e ght
. . . . transmission was very mmorly impacted. The project ab-
was mentored by teacher Debbie Cooper with a project enti- _ . _ ,
fled “A Novel AP mach to Recognize Emotion from speech stract is available at Ms. Shah also received
. . P . . . . the US Air Force First Place Award in Physics and Astron-
Usmg Machine Learning Algorithms to Aid Social Interac- _ _ _
. . . . ,, . . . omy, the National Security Agency (NSA) Research Direc-
tion of Kids with Autism. The goal of this project was to aid _ _ _
. . . . . . torate Physical Sciences First Place Award, and the Intel
autistic children in their development of empathy and social _
. . . ISEF Best of Physics and Astronomy Category Fourth Place
interactions by using cues from speech to help compensate A d
for difficulties in reading facial expressions. Ms. Mukher— war '
jee’s contribution over previous work was developing a heu- An 11th grader, Gabrielle Liu (Systems Software Category),
ristic weighting of the mel-frequency cepstral coeflicients from Ravenwood  School, Brentwood, TN, and men-
(MFCCs) that improve classifier accuracy by an additional tored by teacher Peter Lowen, took third place. Ms. Liu’s
3-12%. She investigated a number of machine-learning al- project, “Preventing Domestic Violence Using Emotion
gorithms and found that the multinomial logistic regression Recognition in Speech” also used machine learning to moni-
provided the most accuracy for her metrics. Her system was tor emotions but as a screen to pick up domestic violence.
trained and tested using a database of expressive speech. See She envisions incorporating her algorithms in the burgeon-
her full project abstract at Ms. Mukherjee ing prevalent use of artificial intelligence personal assistants.
Winter 2018 | Acoustics Thday | E7

   67   68   69   70   71