Research Engineer, Speech Technology and Research Laboratory
Andreas Tsiartas, Ph.D., has research interests that include speech cues analysis, cognitive state representation, speech-to-speech translation, acoustic and language modeling, and speech signals representation.
He holds a B.Sc. degree in electronics and computer engineering from the Technical University of Crete. He also holds an MSc. and a Ph.D. in signal processing from the Department of Electrical Engineering (EE), University of Southern California (USC). He has published more than 20 papers in the field of speech processing.
Tsiartas’ honors and awards include best teaching assistant awards in 2009 and 2010 from EE, USC. In 2006, he was awarded the Viterbi School Dean’s Doctoral Fellowship from USC.
Recent publicationsmore +
This study demonstrates that a speech-based algorithm can objectively differentiate PTSD cases from controls.
To address the challenge of mapping characteristics of individuals’ speech to information about the group, we coded behavioral and learning-related indicators of collaboration at the individual level.
We describe the methodology for the collection and annotation of a large corpus of emotional speech data through crowdsourcing.
Speech conveys many things beyond content, including aspects of stance and attitude that have not been much studied.
We predict HR from speech using the SRI BioFrustration Corpus.In contrast to previous studies we use continuous spontaneous speech as input.
This work investigates whether nonlexical information from speech can automatically predict the quality of small-group collaborations. Audio was collected from students as they collaborated in groups of three to solve math problems.