Scanning methods and language modeling for binary switch typing

We present preliminary experiments of a binary-switch, static-grid typing interface making use of varying language model contributions. Our motivation is to quantify the degree to which language models can make the simplest scanning interfaces - such as showing one symbol at a time rather than a scanning a grid - competitive in terms of typing speed. We present a grid scanning method making use of optimal Huffman binary codes, and demonstrate the impact of higher order language models on its performance. We also investigate the scanning methods of highlighting just one cell in a grid at any given time or showing one symbol at a time without a grid, and show that they yield commensurate performance when using higher order n-gram models, mainly due to lower error rate and a lower rate of missed targets.