Huffman scanning: using language models within fixed-grid keyboard emulation.

Individuals with severe motor impairments commonly enter text using a single binary switch and symbol scanning methods. We present a new scanning method -Huffman scanning - which uses Huffman coding to select the symbols to highlight during scanning, thus minimizing the expected bits per symbol. With our method, the user can select the intended symbol even after switch activation errors. We describe two varieties of Huffman scanning - synchronous and asynchronous -and present experimental results, demonstrating speedups over row/column and linear scanning.