TY - GEN
T1 - At a Different Pace
T2 - 23rd International ACM SIGACCESS Conference on Computers and Accessibility, ASSETS 2021
AU - Al-Khazraji, Sedeeq
AU - Dingman, Becca
AU - Lee, Sooyeon
AU - Huenerfauth, Matt
N1 - Publisher Copyright:
© 2021 ACM.
PY - 2021/10/17
Y1 - 2021/10/17
N2 - Adding American Sign Language (ASL) versions of information content to websites can improve information accessibility for many people who are Deaf or Hard of Hearing (DHH) who may have lower levels of English literacy. Generating animations from a script representation would enable this content to be easily updated, yet software is needed that can set detailed speed and timing parameters for such animations, which prior work has revealed to be critical for their understandability and acceptance among DHH users. Despite recent work on predicting these parameters using AI models trained on recordings of human signers, no prior work had examined whether DHH users actually prefer for these speed and timing properties to be similar to humans, or to be exaggerated, e.g. for additional clarity. We conducted two empirical studies to investigate preferences of ASL signers for speed and timing parameters of ASL animations, including: Sign duration, transition time, differential signing rate, pause length, and pausing frequency. Our first study (N=20) identified two preferred values from among five options for each parameter, one of which included a typical human value for this parameter, and a second study (N=20) identified the most preferred value. We found that while ASL signers preferred pause length and frequency to be similar to those of humans, they actually preferred animations to have faster signs, slower transitions, and less dynamic variation in differential signing speed, as compared to the timing of human signers. This study provides specific empirical guidance for creators of future ASL animation technologies, and more broadly, it demonstrates that it is not safe to assume that ASL signers will simply prefer for properties of ASL animations to be as similar as possible to human signers.
AB - Adding American Sign Language (ASL) versions of information content to websites can improve information accessibility for many people who are Deaf or Hard of Hearing (DHH) who may have lower levels of English literacy. Generating animations from a script representation would enable this content to be easily updated, yet software is needed that can set detailed speed and timing parameters for such animations, which prior work has revealed to be critical for their understandability and acceptance among DHH users. Despite recent work on predicting these parameters using AI models trained on recordings of human signers, no prior work had examined whether DHH users actually prefer for these speed and timing properties to be similar to humans, or to be exaggerated, e.g. for additional clarity. We conducted two empirical studies to investigate preferences of ASL signers for speed and timing parameters of ASL animations, including: Sign duration, transition time, differential signing rate, pause length, and pausing frequency. Our first study (N=20) identified two preferred values from among five options for each parameter, one of which included a typical human value for this parameter, and a second study (N=20) identified the most preferred value. We found that while ASL signers preferred pause length and frequency to be similar to those of humans, they actually preferred animations to have faster signs, slower transitions, and less dynamic variation in differential signing speed, as compared to the timing of human signers. This study provides specific empirical guidance for creators of future ASL animation technologies, and more broadly, it demonstrates that it is not safe to assume that ASL signers will simply prefer for properties of ASL animations to be as similar as possible to human signers.
KW - ASL
KW - American Sign Language
KW - Animation
KW - Modeling.
KW - Prosodic Breaks
KW - Speed
KW - Timing
UR - http://www.scopus.com/inward/record.url?scp=85119270960&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85119270960&partnerID=8YFLogxK
U2 - 10.1145/3441852.3471214
DO - 10.1145/3441852.3471214
M3 - Conference contribution
AN - SCOPUS:85119270960
T3 - ASSETS 2021 - 23rd International ACM SIGACCESS Conference on Computers and Accessibility
BT - ASSETS 2021 - 23rd International ACM SIGACCESS Conference on Computers and Accessibility
PB - Association for Computing Machinery, Inc
Y2 - 18 October 2021 through 22 October 2021
ER -