Huffman and Linear Scanning Methods with Statistical Language Models

Abstract

Current scanning access methods for text generation in AAC devices are limited to relatively few options, most notably row/column variations within a matrix. We present Huffman scanning, a new method for applying statistical language models to binary-switch, static-grid typing AAC interfaces, and compare it to other scanning options under a variety of conditions. We present results for 16 adults without disabilities and one 36-year-old man with locked-in syndrome who presents with complex communication needs and uses AAC scanning devices for writing. Huffman scanning with a statistical language model yielded significant typing speedups for the 16 participants without disabilities versus any of the other methods tested, including two row/column scanning methods. A similar pattern of results was found with the individual with locked-in syndrome. Interestingly, faster typing speeds were obtained with Huffman scanning using a more leisurely scan rate than relatively fast individually calibrated scan rates. Overall, the results reported here demonstrate great promise for the usability of Huffman scanning as a faster alternative to row/column scanning.

Keywords::

• Scanning
• Natural language processing
• Augmentative and alternative communication (AAC)

Acknowledgements

We thank GB for taking the time to participate in this series of scanning experiments.

Notes

Declaration of interest: The authors report no conflicts of interest. The authors are responsible for the content and writing of the paper.

We acknowledge support from NIH/NIDCD grant 1R01DC009834.

Notes

1. The RSVP Keyboard^™ is a P300 brain–computer interface spelling system that is being developed at Oregon Health & Science University under an NIH grant (5R01DC009834) to Dr Fried-Oken, principal investigator.

2. The Words+ Freedom 2000^TM speech generating device and EZ Keys^TM software were manufactured and sold by Words+, Inc. of Lancaster, CA, USA.

3. The Specs^TM Switch is manufactured and sold by AbleNet, Inc. of Roseville, MN, USA.

4. The Universal Switch Mounting System^TM is manufactured and sold by AbleNet, Inc. of Roseville, MN, USA.

5. The Jelly Bean Switch^TM is manufactured and sold by AbleNet, Inc. of Roseville, MN, USA.

6. Apple IIe computer is the third model Apple II series of personal computers produced by Apple Computer of Cupertino, CA, USA.

7. Discover: KENX is a keyboard interface designed to access a computer using a choice of methods other than a standard keyboard that was manufactured by Don Johnston Inc. of Volo, IL, USA, and is a trademark of Madentec Limited, of Edmonton, Alberta, Canada.

8. Co:Writer is word prediction software manufactured by Don Johnston Inc. of Volo, IL, USA.