1 Disability and Rehabilitation: Assistive Technology, 2011, 1–7, Early Online Copyright © 2011 Informa UK, Ltd. ISSN 1748-3107 print/ISSN 1748-3115 online DOI: 10.3109/17483107.2011.629330 Purpose: A recently-developed assistive technology nicknamed “the Hummer” was investigated as a potential powered wheelchair controller for individuals with severe and multiple disabilities. System performance in a noisy environment was compared to that obtained with a commercial automatic speech recognition (ASR) system. Method: A bi-hum driving protocol was developed to allow the Hummer to serve as a powered wheelchair controller. Participants performed several virtual wheelchair driving tasks of increasing difficulty using the two systems. Custom-written software recorded task execution time, number of commands issued and wall collisions, speed, and trajectory. Results: The bi-hum protocol was shown to be non-intuitive and required user training. Overall, the Hummer achieved lower performance relative to ASR. Once users became accustomed to the protocol, the difference in performance between the two systems became insignificant, particularly for the higher-difficulty task. Conclusions: The Hummer provides a promising new alternative for powered wheelchair control in everyday environments for individuals with severe and multiple disabilities who are able to hum, particularly for those with severe dysarthria which precludes ASR usage. A more intuitive driving protocol is still needed to reduce user frustration and mitigate user-generated errors; recommendations on how this can be achieved are given herein. Keywords: Ambient noise, assistive technology, automatic speech recognition, powered wheelchair control, vocal cord vibration Introduction Today, approximately 6 million people in the United States are reported to be living with some kind of paralysis; 1.28 million of those are due to spinal cord injury (SCI) [1]. Of these indi- viduals, 36% have reported “a lot of difculty in mobility” and 16% as being “completely unable to move” [1]. Worldwide, as much as 33% of individuals with SCI are completely unable to move and need continuous care [2]. Technological, as well as medical progress, however, has drastically improved their quality of life, as well as allowed them to regain some independent mobility [1]. Representative technologies used for powered wheelchair control, for example, include tongue movement controllers (e.g. [3,4]), brain-computer interfaces [5], breath pressure [6] and snifng [7] controllers, and speech recognition, either used alone (e.g. [8,9]) or in combination with humming for speed control [10]. Automatic speech recognition (ASR) has been researched for the last fve decades, but only with the advances in com- puting power witnessed in the last decade, has ASR become mainstream and subsequently introduced in assistive devices [11]. Surveys with ASR users in the assistive technology realm (e.g. to use a computer), such as individuals with SCI, have suggested high satisfaction rates as well as positive percep- tion of psychosocial impact [12,13]. When ASR is used for more safety-critical functions, however, such as controlling a powered wheelchair, satisfaction rates are much lower, with the majority of respondents using switch-operated systems as a backup [14]. Ambient noise (e.g. crowd noise, wind), user-generated noise (e.g. coughs, airways congestion, heavy breathing), and speech disorders (e.g. affecting as much as 50% of RESEARCH ARTICLE Evaluation of an ambient noise insensitive hum-based powered wheelchair controller Tiago H. Falk 1,2 , Alex Andrews 2 , Fanny Hotzé 2 , Eric Wan 2 & Tom Chau 2 1 Institut National de la Recherche Scientifique, University of Quebec, Montreal, Quebec and and 2 Bloorview Research Institute, Holland Bloorview Kids Rehabilitation Hospital, University of Toronto, Toronto, Ontario, Canada Correspondence: Tiago H. Falk, Institut National de la Recherche Scientifque, University of Quebec 800 rue de la Gauchetiere West, Suite 6900, Montreal, Quebec, H5A-1K6, Canada. Tel: +1 (514) 228-7022. Fax: +1 (514) 875-0344. Email: tiago.falk@ieee.org Te “Hummer” allows for noise-insensitive powered • wheelchair control in everyday environments Te “Hummer” accommodates individuals without • functional speech or those with severe dysarthria to gain mobility independence, thus improving their quality of life. Implications for Rehabilitation Disabil Rehabil Assist Technol Downloaded from informahealthcare.com by Queens University on 02/16/12 For personal use only.