Huffman scanning: Using language models within fixed-grid keyboard emulation

Brian Roark; Russell Beckley; Chris Gibbons; Melanie Fried-Oken

doi:10.1016/j.csl.2012.10.006

Huffman scanning: Using language models within fixed-grid keyboard emulation

Brian Roark, Russell Beckley, Chris Gibbons, Melanie Fried-Oken

Institute on Development and Disability

Research output: Contribution to journal › Article › peer-review

12 Scopus citations

Abstract

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.

Original language	English (US)
Pages (from-to)	1212-1234
Number of pages	23
Journal	Computer Speech and Language
Volume	27
Issue number	6
DOIs	https://doi.org/10.1016/j.csl.2012.10.006
State	Published - 2013

Keywords

Binary coding
Language modeling
Text entry
emulation

ASJC Scopus subject areas

Software
Theoretical Computer Science
Human-Computer Interaction

Access to Document

10.1016/j.csl.2012.10.006

Cite this

@article{545fcc9e390c41848b7f4c8d0c8ad6fc,

title = "Huffman scanning: Using language models within fixed-grid keyboard emulation",

abstract = "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.",

keywords = "Binary coding, Language modeling, Text entry, emulation",

author = "Brian Roark and Russell Beckley and Chris Gibbons and Melanie Fried-Oken",

note = "Funding Information: This research was supported in part by NIH Grant #1R01DC009834-01 and NSF Grant #IIS-0447214 . Any opinions, findings, conclusions or recommendations expressed in this publication are those of the authors and do not necessarily reflect the views of the NSF or NIH. ",

year = "2013",

doi = "10.1016/j.csl.2012.10.006",

language = "English (US)",

volume = "27",

pages = "1212--1234",

journal = "Computer Speech and Language",

issn = "0885-2308",

publisher = "Academic Press Inc.",

number = "6",

}

TY - JOUR

T1 - Huffman scanning

T2 - Using language models within fixed-grid keyboard emulation

AU - Roark, Brian

AU - Beckley, Russell

AU - Gibbons, Chris

AU - Fried-Oken, Melanie

N1 - Funding Information: This research was supported in part by NIH Grant #1R01DC009834-01 and NSF Grant #IIS-0447214 . Any opinions, findings, conclusions or recommendations expressed in this publication are those of the authors and do not necessarily reflect the views of the NSF or NIH.

PY - 2013

Y1 - 2013

N2 - 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.

AB - 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.

KW - Binary coding

KW - Language modeling

KW - Text entry

KW - emulation

UR - http://www.scopus.com/inward/record.url?scp=84879079154&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84879079154&partnerID=8YFLogxK

U2 - 10.1016/j.csl.2012.10.006

DO - 10.1016/j.csl.2012.10.006

M3 - Article

AN - SCOPUS:84879079154

SN - 0885-2308

VL - 27

SP - 1212

EP - 1234

JO - Computer Speech and Language

JF - Computer Speech and Language

IS - 6

ER -

Huffman scanning: Using language models within fixed-grid keyboard emulation

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this