About our Research Group

Aspire, Develop, Create, Impact, Encourage, Lead

The ASPIRE Group strives to develop scientifically sound ideas and the next generation of impactful researchers.

The Audio, Speech, and Perceptually-Inspired Research (ASPIRE) Group at The Ohio State University has a long-standing goal of developing intelligent sound-processing approaches that continuously learn from user and environmental data in real-world settings. This is accomplished through the development of algorithms that analyze data, extract meaningful information, and make predictions from speech, neurophysiological, and human-provided inputs. Our research draws on concepts from deep learning, artificial intelligence, and signal processing.

More specifically, our group works on projects involving speech enhancement and noise reduction, Electroencephalography (EEG)-guided attended speaker extraction, and computational modeling of human speech assessment. We are also interested in conducting behavioral studies with human participants for data collection and algorithm evaluation. In addition, we develop explainable AI methods to better understand and interpret algorithmic decision-making.

These efforts have resulted in publications and presentations at top-tier venues. Our research has been supported by the National Science Foundation (NSF), the U.S. Department of Defense, and the Toyota Research Institute. We have also received seed funding from The Ohio State University and Indiana University.

Research Opportunities

Current Openings

Prospective Ph.D. students

We are always seeking highly motivated and hardworking Ph.D. students whose interests and experiences align closely with those of our research group. Prospective students are expected to have a background in computer science, electrical engineering, speech and hearing science, or closely related fields involving areas such as neurophysiology or psychoacoustics.

If you are interested in joining the group, you should apply through the Department of Computer Science and Engineering (CSE) and mention Dr. Williamson's name in your application materials. You should also contact Dr. Williamson with a brief description of your background, research experience, and research interests, and explain how they align with the group's current research efforts. Please include a copy of your CV.

If there appears to be a strong match between your interests and the group's research directions, we will contact you to discuss potential opportunities further.


Prospective M.S. and Undergraduate students

We typically work with M.S. and undergraduate students who have already taken a course with Dr. Williamson. As such, we encourage interested students to enroll in one of his courses first. Doing so will help you learn more about the field, determine whether the research aligns with your interests, and provide an opportunity for Dr. Williamson to get to know you and your strengths as a student.

Our Main Research Areas

We focus on projects that impact how people communicate with each other and to devices through speech.

Speech Extraction

We develop deep learning algorithms for robust speech extraction in complex acoustic environments. Our algorithms are guided by perceptual and neurophysiological inputs.

Speech Assessment

Speech assessment approaches are needed that facilitate real-world evaluation while accurately modeling human perceptions of speech quality and intelligibility.

Explainabale AI

Developing explainable frameworks that provide interpretable insights into speech extraction and assessment outcomes, to better understand, validate, and improve model behavior.

© 2026 The ASPIRE Group. All Rights Reserved | Design by W3layouts