scispace - formally typeset
P

Panayiotis G. Georgiou

Researcher at University of Southern California

Publications -  232
Citations -  4873

Panayiotis G. Georgiou is an academic researcher from University of Southern California. The author has contributed to research in topics: Language model & Speech processing. The author has an hindex of 30, co-authored 230 publications receiving 4076 citations. Previous affiliations of Panayiotis G. Georgiou include Apple Inc. & Steel Authority of India.

Papers
More filters
Journal ArticleDOI

Behavioral Signal Processing: Deriving Human Behavioral Informatics From Speech and Language

TL;DR: Behavioral informatics applications of these signal processing techniques that contribute to quantifying higher level, often subjectively described, human behavior in a domain-sensitive fashion are illustrated.
Journal ArticleDOI

Alpha-stable modeling of noise and robust time-delay estimation in the presence of impulsive noise

TL;DR: A new representation of audio noise signals is proposed, based on symmetric /spl alpha/-stable (S/spl alpha/S) distributions in order to better model the outliers that exist in real signals.
Journal ArticleDOI

Proceedings from the 9th annual conference on the science of dissemination and implementation

David A. Chambers, +382 more
TL;DR: A1 Introduction to the 8th Annual Conference on the Science of Dissemination and Implementation: Optimizing Personal and Population Health.
Patent

Socially cognizant translation by detecting and transforming elements of politeness and respect

TL;DR: A socially cognizant translation system that takes social state between speaker and listener into account when making the translation is proposed in this article, where the source speech can be translated without the profanity in the target language, instead using the meaning of profanity.

SailAlign: Robust long speech-text alignment

TL;DR: SailAlign is an open-source software toolkit for robust long speech-text alignment that allows for the processing of very long (and possibly noisy) audio and is robust to transcription errors and is evaluated on artificial ly created long chunks of the TIMIT database.