Speech Recognition

Speech Recognition Technologies Abstract While commercial solutions for precise indoor positioning exist, they are costly and require installation of additional infrastructure, which limits opportunities for widespread adoption. Inspired by robotics techniques of Simultaneous Localization and Mapping (SLAM) and computer vision approaches using structured light patterns, we propose a self-contained solution to precise indoor positioning that requires no additional environmental infrastructure. Evaluation of our prototype, called TrackSense, indicates that such a system can deliver up to 4 cm accuracy with 3 cm precision in rooms up to five meters squared, as well as 2 degree accuracy and 1 degree precision on orientation. We explain the design and performance characteristics of our prototype and demonstrate a feasible miniaturization that supports applications that require a single device localizing itself in a space. We also discuss extensions to locate multiple devices and limitations of this approach. 2. Introduction We introduce a solution to indoor localization, TrackSense, that requires no additional infrastructure in the environment and provides 3D positioning and orientation data that performs well against existing research and commercial solutions. Although we have seen great progress toward the goal of indoor localization, almost all of the solutions that offer precise (few centimeter) indoor localization have been limited to techniques that require the introduction of new infrastructure to the physical space (e.g. cameras or beacons). These solutions are often costly and typically require time-consuming installations, and it is not easy to move the instrumentation from one space to another. Although existing commercial positioning systems are adequate for prototyping user experiences, their ultimate success relies on a localization approach that is inexpensive and easily deployed. 3. Accuracy It is notoriously difficult to measure the accuracy of speech

References: www.uclan.ac.uk/facs/destech/compute/staff/read/Publish/read.pdf - Measuring the usability of text input methods for children - A comparison of speech recognition and three other methods of data entry. While the research revealed interesting observations about how the systems were used and reacted to input, the authors (as with several similar comparative papers in this field) shied away from an overall this is best conclusion. www.vhml.org/workshops/HF2002/papers/broughton/broughton.pdf - Measuring the accuracy of commercial automated speech recognition systems during conversational speech - for a number of stated factors, the accuracy in the experiment did not match that quoted by the software. www.womengamers.com/revprev/sim/seaman.html - Review of Seaman (2000) for the Sega Dreamcast. reviews.zdnet.co.uk/review/43/2/1605.html - review of Dragon NaturallySpeaking Preferred 6.0 www.uow.edu.au/student/services/uow/VRSoftware.html - a university-authored guide to the training process involved in using the speech recognition software it provides. www.ceangal.com/ www.furui.cs.titech.ac.jp/publication/2000/icassp2000-3735.pdf - Speech recognition technology in the ubiquitous wearable computing environment. An analysis of the potential, and current problems, of wearable computers that could be operated through speech recognition technology.