Projects - Multimodal Signal Processing (MSP) Laboratory

National Science Fundation (NSF)

"EAGER: Exploring the Use of Synthetic Speech as Reference Model to Detect Salient Emotional Segments in Speech,"
Mar. 2013-Aug. 2014
This exploratory analysis aims to create neutral reference model from synthetic speech to contrast the emotional content of a speech signal.

Samsung Telecommunications America, LLC

"Advancements in Automatic Speech Recognition: Corpus Development, Model Training, Dialect/Accent, and Hands-Free Interaction"
Nov. 2012-Dec. 2013
The project focuses on advancements to improve various aspects of both small and large vocabulary continuous speech recognition (LVCSR).

National Science Fundation (NSF)

"Exploring Audiovisual Emotion Perception using Data-Driven Computational Modeling"
Sep. 2012-Aug. 2014
This project explores perceptual-based models for emotion behavior assessments through the study of human audio-visual emotion perception using statistical analyses, data-driven computational modeling, and implicit sensing.

Samsung Telecommunications America, LLC

"Standardization of Advanced User Interface for Mobile Devices"
Sep. 2011-Sep. 2012
The project studies the scope of advanced user interfaces' standard for mobile devices, and the essential technologies for it.