Hynek Boril, Ph.D.
Associate Professor
Electrical and Computer Engineering Department
University of Wisconsin-Platteville
CURRENT ACTIVITIES
July 20-22, 2022
International Conference on Electrical, Computer and Energy Technologies - IEEE ICECET 2022 (Prague, Czech Republic)
Presented a study 'GAN-Based Augmentation for Gender Classification from Speech Spectrograms' done with my UW-Platteville student Skyler Horn. We explored the impact of augmenting training datasets with GAN-generated synthetic spectrograms on the example of female vs. male gender detection from speech. The paper shows that the augmentation scheme is surprisingly effective, especially when only limited authentic data are available for both the classifier training and the GAN generator training. We also explored gender classification performance as a function of noise level and classifier network architecutre (CNN vs. fully-connected).December 8-10, 2021
PSSPL Student Group Presentation at UT-Dallas (Richardson, Texas)
Brought a group of 6 undergraduate researchers from Pioneer Speech Signal Processing Lab (PSSPL)/UW-Plattevile to present our projects to our partnering laboratory-the Center for Robust Speech Systems (CRSS) at UT-Dallas. Our students got to tour several ECE graduate research labs focused on signal processing, machine learning, multimodal systems, controls, as well as Mechanical Engineering department labs working on autonomous vehicles and renewable energy. It was also great to meet Dr. Adams, the Dean of Erik Jonsson School of Engineering and Computer Science, who was passionate in talking to our students and encouraging them to pursue graduate studies. There are currently 9 UW-Plattevile ECE alumni pursuing PhD at UT-Dallas with full suport!October 11-13, 2021
AES Convention'21 (Las Vegas, Nevada)
Presented a paper 'Gunshot Detection Systems: Methods, Challenges, and Can they be Trusted?' done with Dr. Hansen (CRSS/UT-Dallas). Gunshot detection systems are deployed in over a 100 cities in the US and world-wide and are routinely used to trigger alerts and dispatch law enformecement to locations of suspected gun violence. Information produced by these systems is often used as sumplementary evidence in criminal prosecutions. Our paper looks under the hood of these systems and investigates their trustworthiness and possible limitations.August 30-September 3, 2021
ISCA INTERSPEECH'21 (Brno, Czech)
Co-chaired a session "Voice Activity Detection" together with Dr. Hansen (CRSS/UT-Dallas). My first in-person conference since the pandemic started! The sessions were fantastic and it was great to reconnect with colleagues, including former PhD labmates from CTU in Prague.
Welcome To My Homepage
About Me
I was born in Most, Czech Republic and received the M.S. degree in electrical engineering and Ph.D. degree in electrical engineering and information technology from the Department of Electrical Engineering, Czech Technical University in Prague, in 2003 and 2008, respectively. In August 2007, I joined the Center for Robust Speech Systems (CRSS), Eric Jonsson School of Engineering and Computer Science, University of Texas at Dallas, as a Research Associate and in 2012 as an Assistant Research Professor. Since August 2015, I was with the Electrical and Computer Engineering Department at the University of Wisconsin-Platteville as an Assistant Professor and since August 2021, I have been an Associate Professor. Since August 2015, I have been also an Adjunct Research Faculty at CRSS, UT-Dallas. At UW-Platteville, I established the Pioneer Speech Signal Processing Laboratory (PSSPL) whose mission is to engage undergraduate students in research on speech technologies and connect them with graduate institutions and industry. I have authored/co-authored over 60 journal and conference papers. My research interests span the areas of digital signal processing, acoustic signal modeling, and machine learning, with the focus on automatic speech and speaker recognition, language and dialect identification, stress, emotion and cognitive load classification, automatic assessment of physiological traits from speech signals, robustness to environmental and speaker-induced variability, and language acquisition in infants. I served as an external reviewer for the U.S. Department of Homeland Security's Office of University Programs-Criminal Investigations and Network Analysis (CINA), Dutch Research Council/Netherlands Organization for Scientific Research (NWO) Talent Programme-Veni Scheme, and Ministry of Business, Innovation, and Employment of New Zealand (MBIE) Science Investment Round and was on the Editorial Advisory Board of the book 'Technologies for Inclusive Education: Beyond Traditional Integration Approaches' (Eds. D. Griol, Z. Callejas, R. L. Cozar) IGI Global, 2012. I was an independent expert in two patent infringement cases in the field of automatic speech and speaker recognition, two patent validity reexamination cases in the field of automatic speech recognition, a voice forensics case, and a feasibility/reliability study of gunshot detection systems.
Research Interests
Automatic Speech/Speaker/Language and Dialect Recognition
- Vocal effort (Lombard effect/whisper), noise, and channel variability
- Robust feature extraction front-ends
- Online feature equalization
- Acoustic modeling for varying environments
- Limited resource tasks
Speech Analysis/Modeling/Assessment
- Stress, cognitive load and emotions in human-human and human-machine interactions
- Phonotactic modeling for language and dialect identification
- Language acquisition in infants
- Physiological traits in speech signals
Music Signal Processing
- High-precision pitch tracking for real-time acoustic signal transcription and audio-to-MIDI conversion
Last Updated 2-18-2022