The Audio, Speech and Perceptually-Inspired REsearch (ASPIRE) Group @ The Ohio State University has the long-standing goal of developing intelligent sount processing approaches that continually learn from user and environmental data in real-world environments, while also preserving user privacy. This is being accomplished by producing algorithms that analyze, extract meaningful information, and that make predictions from audio, speech and signal data. Our approaches involve advanced probabilistic, signal processing, and deep learning concepts. More specifically, our group works on projects that remove unwanted background noise from speech, analyze/estimate auditory speech assessment, and projects that develop mechanisms for ensuring audio and speech privacy for consumer electronic devices. These efforts have resulted in presentations and papers at top-tier venues. Our work has been supported by the National Science Foundation (NSF) through a Computer and Information Science and Engineering (CISE) Research Initiation Initative (CRII) award , through a CAREER award , an Indiana University Faculty Research Support Program - Seed Funding (FRSP-SF) award, and by the Toyota Research Institute.
We also strive to aspire the next generation of researchers to pursue careers in computer science, engineering and machine learning, especially for individuals from traditionally underrepresented groups. Throughout the year, our members participate in various outreach efforts that introduce young students to computer science and engineering, while also providing them with necessary skills for success.
Data-driven, property-preserving and adaptable algorithms are developed to separate and detect different components of a signal.
Audio and speech assessment approaches are needed that enable real-world evaluation and that model human assessment behavior.
© 2024 The ASPIRE Group. All Rights Reserved | Design by W3layouts