Acoustic landmarks are defined as patterns that profile various speech production events. In this project, I will analyze natural speech from the linguistic perspective by leveraging acoustic landmarks to better understand how speech can be segmented and classified. Then, I will integrate this linguistic approach with novel NLP and ML techniques to develop a model that processes speech in accordance with human perceptual benchmarks. This requires an understanding of both the low-level phonological decomposition and high-level probabilistic approaches necessary to analyze speech psycholinguistically. This model can then be applied to fields such as speech disorder diagnostics, emotion recognition, and interactive voice systems.

I am participating in SuperUROP to experience end-to-end research in a field of interest, Speech Processing. My project will utilize theory from some of my favorite courses at MIT: 9.35 (Perception), 6.390 (ML), and 24.900 (Linguistics), alongside skills and interests such as Signal Processing and Acoustic Phonetics. I ultimately hope to produce research that is both computationally robust and aligned with underlying psycholinguistic theory.