Huffman and linear scanning methods with statistical language models

Brian Roark, Melanie Fried-Oken, Chris Gibbons

Research output: Contribution to journalArticle

5 Citations (Scopus)

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.

Original languageEnglish (US)
Pages (from-to)37-50
Number of pages14
JournalAAC: Augmentative and Alternative Communication
Volume31
Issue number1
DOIs
StatePublished - Mar 1 2015

Fingerprint

Statistical Models
Language
Quadriplegia
Equipment and Supplies
Communication

Keywords

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

ASJC Scopus subject areas

  • Rehabilitation
  • Speech and Hearing

Cite this

Huffman and linear scanning methods with statistical language models. / Roark, Brian; Fried-Oken, Melanie; Gibbons, Chris.

In: AAC: Augmentative and Alternative Communication, Vol. 31, No. 1, 01.03.2015, p. 37-50.

Research output: Contribution to journalArticle

@article{8fe5801bd52046bab5c61a1e4008230a,
title = "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 = "Augmentative and alternative communication (AAC), Natural language processing, Scanning",
author = "Brian Roark and Melanie Fried-Oken and Chris Gibbons",
year = "2015",
month = "3",
day = "1",
doi = "10.3109/07434618.2014.997890",
language = "English (US)",
volume = "31",
pages = "37--50",
journal = "AAC: Augmentative and Alternative Communication",
issn = "0743-4618",
publisher = "Informa Healthcare",
number = "1",

}

TY - JOUR

T1 - Huffman and linear scanning methods with statistical language models

AU - Roark, Brian

AU - Fried-Oken, Melanie

AU - Gibbons, Chris

PY - 2015/3/1

Y1 - 2015/3/1

N2 - 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.

AB - 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.

KW - Augmentative and alternative communication (AAC)

KW - Natural language processing

KW - Scanning

UR - http://www.scopus.com/inward/record.url?scp=84923096801&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84923096801&partnerID=8YFLogxK

U2 - 10.3109/07434618.2014.997890

DO - 10.3109/07434618.2014.997890

M3 - Article

VL - 31

SP - 37

EP - 50

JO - AAC: Augmentative and Alternative Communication

JF - AAC: Augmentative and Alternative Communication

SN - 0743-4618

IS - 1

ER -