Title :
Selection of Unknown Objects Specified by Speech Using Models Constructed from Web Images
Author :
Nishimura, H. ; Ozasa, Y. ; Ariki, Y. ; Nakano, M.
Author_Institution :
Grad. Sch. of Syst. Inf., Kobe Univ., Kobe, Japan
Abstract :
To select an object requested by human voice among several unknown objects is one of the important tasks for household robots that assist human´s daily lives. In this paper, we propose a method that can achieve this task. Using image models which are constructed by Web images collected from the results of speech recognition, the proposed method enables a robot to select an object specified by a speech from several unknown objects in a real environment.
Keywords :
Internet; service robots; speech processing; Web images; household robots; human voice; image models; real environment; speech recognition; unknown objects; Accuracy; Hidden Markov models; Image recognition; Logistics; Robots; Speech; Speech recognition; Web images; multimodality; object recognition;
Conference_Titel :
Pattern Recognition (ICPR), 2014 22nd International Conference on
Conference_Location :
Stockholm
DOI :
10.1109/ICPR.2014.91
