Machine Learning for Spoken Language Technology

Abstract

Spoken language technology is one of the domains in which, in our days, machine learning algorithms and especially neural networks are used. Some applications will pe presented in this paper: detecting overlapped speech on short time frames (till 25ms), emotion recognition from speech (including speech stress detection and deceptive speech detection) and the performances of the last large vocabulary continuous speech recognition systems for Romanian developed in the SpeeD Laboratory, from Research Institute “CAMPUS”, University POLITEHNICA of Bucharest