Resume¶
Dan G. Jacobellis | danjacobellis@utexas.edu
Education¶
Pursuing PhD in Electrical Engineering • University of Texas at Austin • 2021-Present • GPA: 3.65
Notable Coursework:
Information Theory
Digital Video Processing
Spoken Language Technologies
Physical Acoustics
Statistical Machine Learning
Data Mining
Parallel Algorithms
Computational Methods for Inverse Problems
M.S. Electrical Engineering • University of Texas at Austin • 2018-2021 • GPA: 3.67
B.S. Electrical Engineering • University of Texas at Austin • 2013-2018 • GPA: 3.71
Awards¶
2022 Top Student Teaching award, ECE Department¶
Awarded in recognition of excellence in teaching as a teaching assistant for ECE 445S Real-time Digital Signal Processing Lab.
2019 Research Excellence Award, Applied Research Laboratories¶
Annual award in recognition of outstanding research efforts based on nomination from peers and colleagues.
Experience¶
Applied Research Laboratories, University of Texas at Austin¶
Graduate Research Assistant • 2018 – 2022
Research Engineering Scientist Associate • 2017 – 2018
Student Technician • 2015 - 2017
Developed software and performed underwater acoustics research for the Environmental Science Laboratory. Work included:
Development of MATLAB software tools to perform geoacoustic inversion
Analysis of newly collected data from passive acoustic sensor arrays
Software performance optimization for large computing clusters
Researching new methods to quantify uncertainty of ocean acoustic propagation models
ECE Department, University of Texas at Austin¶
Graduate Teaching Assistant • 2019 – Present
Graduate Research Assistant • 2021 – 2022
I am a teaching assistant for ECE 445S Digital Signal Processing Lab. Along with another gradute TA, I lead the laboratory section of the class where components of a software defined radio system are implemented.
In addition to my TA position, I was appointed as a GRA to develop new course materials. When courses were moved online due to COVID-19, I assisted in restructuring the lab work so that it could be completed online using the audio hardware built into students’ personal computers. With the return to in-person classes is 2021, I developed a new lab manual for the course to help transition to new hardware. My contributions include
Development of starter code and tutorials for programming the Cortex-M7 based STM32 development board
New, concise explanations of DSP topics including
Dozens of new figures, illustrations, and code examples
Development of new lab exercises, including an acoustic modem and vocoder
Tutorials for using the ARM CMSIS DSP libraries
In Summer 2022 and Fall 2022, I was a teaching assistant for ECE 351K Probability and Statistics.
In Summer 2019, I was a teaching assistant for ECE 313 Linear Systems and Systems. In addition to grading coursework and holding office hours, I held a weekly video-recorded problem solving recitation. I also developed new course materials for the class including:
Rewritten and typeset solutions to over one hundred homework exercises, including additional illustrations and discussion of problems.
Updated MATLAB programming assignments to optionally allow Python
Projects¶
-
Implemented a set of perfect reconstruction filter banks on the GPU which result in a novel type of time-frequency tiling.
GPU accelerated non-negative matrix factorization for audio
Implemented multiplicative update matrix factorization algorithm. Performance on consumer GPU outperforms single-core Scikit-learn/OpenBLAS by a factor of more than 100.
Audio-visual speech separation
Implemented pipeline to process and train on videos from the AVspeech dataset. The model uses visual information to separate the audio of videos containing multiple speakers. The last spatially-varying layer of a face recognition model is used to extract low-dimensional embeddings that characterize the visual component of speech. These are combined with the mixed signal to form the input to convolutional and recurrent network layers that predict the time-frequency separating mask.
Automatic music transcription and instrument classification
Built a dataset of isolated musical instrument recordings to train a classification model. Developed a harmonic template matching algorithm to transcribe polyphonic musical recordings by exploiting structure of equal temperament scale
Video classifier for human activities
Trained a video classifier using recurrent neural network and deployed a web server to use the classifier as a mobile application.
-
Built dataset of over 10,000 images and trained model to identify the type of a food dish and its ethnicity from a photo.
Skills and expertise¶
Programming
Julia
C, C++
Python
MATLAB
Signal Processing
Time-frequency analysis
Wavelets, filter banks
Denoising
Compression
Acoustics
Phased array processing
Inverse problems
Propagation models
Miscellaneous
Cooking
Cello
Sewing