Title :
The self-taught vocal interface
Author :
Gemmeke, Jort F.
Author_Institution :
ESAT-PSI, KU Leuven, Leuven, Belgium
Abstract :
We describe a demonstration of a novel vocal user interface (VUI), ALADIN, which is trained through usage, by demonstrating spoken commands with manual controls. It works by mining the vocal commands to find recurrent acoustic patterns corresponding to words or phrases that constitute elements of the user´s commands. The demonstration consists of the VUI controlling a 3D environment with home automation devices such as lights and doors, as well as an actual home automation setup. Additionally, a tablet interface is provided for feedback and manual control.
Keywords :
data mining; notebook computers; speech recognition; speech-based user interfaces; 3D environment; ALADIN vocal user interface; VUI; home automation devices; manual control; recurrent acoustic patterns; self-taught vocal interface; spoken commands; tablet interface; user commands; vocal command mining; Acoustics; Home automation; Human factors; Microphones; Speech; Three-dimensional displays; Training;
Conference_Titel :
Hands-free Speech Communication and Microphone Arrays (HSCMA), 2014 4th Joint Workshop on
Conference_Location :
Villers-les-Nancy
DOI :
10.1109/HSCMA.2014.6843243
