Speech Recognition Technology in Multimodal/Ubiquitous Computing Environments
In the ubiquitous (pervasive) computing era, it is expected that everybody will access information services anytime anywhere, and these services are expected to augment various human intelligent activities. Speech recognition technology can play an import
- PDF / 1,620,962 Bytes
- 24 Pages / 594.72 x 841.68 pts Page_size
- 74 Downloads / 185 Views
Abstract
In the ubiquitous (pervasive) computing era, it is expected that everybody will access information services anytime anywhere, and these services are expected to augment various human intelligent activities. Speech recognition technology can play an important role in this era by providing: (a) conversational systems for accessing information services and (b) systems for transcribing, understanding and summarising ubiquitous speech documents such as meetings, lectures, presentations and voicemails. In the former systems, robust conversation using wireless handheld/hands-free devices in the real mobile computing environment will be crucial, as will multimodal speech recognition technology. To create the latter systems, the ability to understand and summarise speech documents is one of the key requirements. This chapter presents technological perspectives and introduces several research activities being conducted from these standpoints.
Keywords:
Speech understanding; Speech summarisation; Human-computer interaction; Robustness; Adaptation; Spontaneous speech.
1.
Ubiquitous/Wearable Computing Environment
The continuing progress in hardware and software development technologies have lead to the augmentation of computer performance at such a rapid pace that it improves several hundred times in every 10-year period. Resultingly, computers are getting smaller, more powerful and cheaper. Regardless of whether and to what degree they are noticed by users, computers will proliferate into every facet of our daily lives. People will actually walk through their day-to-day lives wearing several computers at a time. Thus, making com13 W. Minker, D. Bühler andL. Dybkjær (eds), Spoken Multimodal Human-Computer Dialogue in Mobile Environments, 13-36 © 2005 Springer. Printed in the Netherlands
14
SPOKEN MULTIMODAL HUMAN-COMPUTER DIALOGUE
puters mobile and portable, exemplified by the present PDA (personal digital assistant) technology, is considered to be the transition phase to wearable computing (Pentland, 1998). Making computers more functional and smaller will generate not only quantitative changes but also qualitative changes in the way we use computers. In the near future, various computers including portable equipment existing everywhere will work together in autonomous collaboration (Weiser, 1991). Indeed, the new characteristics of computing will greatly change the focus and approach of human-computer interaction. The transmission channel capacity of portable terminals will be easily expanded to the level of several Mbps, taking advantage of the technological progress available through, for example, MMAC (Multimedia Mobile Access Communication) systems. The exchange of dynamic information will be possible in addition to that of simple characters and voice information. In turn, this will give rise to sophisticated collaboration and coordination of humanmachine systems based on autonomous protocol and information exchange between computers distributed everywhere.
2.
State-of-the-Art Speech Recognition Techn
Data Loading...
