Ella  Tubbs

Ella Tubbs

Scholar Title

MIT EECS | Philips Undergraduate Research and Innovation Scholar

Research Title

Automatic Detection of Spectral Bursts in Speech Using Cue-Based Analysis

Cohort

2023–2024

Department

EECS

Research Areas
  • Natural Language and Speech Processing
Supervisor

Stefanie Shattuck–Hufnagel

Abstract

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.

Quote

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.

Back to Scholars