Home // SPWID 2018, The Fourth International Conference on Smart Portable, Wearable, Implantable and Disability-oriented Devices and Systems // View article


TouchWear: Context-Dependent and Self-Learning Personal Speech Assistant for Wearable Systems with Deep Neural Networks

Authors:
Joshua Ho
Chien-Min Wang

Keywords: wearable computing; personal speech assistant; context awareness; deep neural network.

Abstract:
Context awareness in future adaptive systems for wearable computers comprise many features, such as ability to sense and perceive contexts, to be inferred by the generation of a user model, to perform the computation and present the communication interface, and to provision implemented services. In this work, we introduce a system application prototype implemented by distinguishing contexts from wearable systems. Thus, user behavior, activity, and application data are trained to generate a user model. Next, a voice interface administered by the artificial personal speech assistant not only enables conversation with the user but is also used to build a recurrent model of deep neural networks primarily based on the conversation logs. Ultimately, the service and recommendation framework are implemented and deployed so that the wearable system has the capacity to aid people in need by means of service-oriented and wearable adaptation.

Pages: 25 to 29

Copyright: Copyright (c) IARIA, 2018

Publication date: July 22, 2018

Published in: conference

ISSN: 2519-8440

ISBN: 978-1-61208-657-6

Location: Barcelona, Spain

Dates: from July 22, 2018 to July 26, 2018