Usage, performance, and satisfaction outcomes for experienced users of automatic speech recognition

Koester, Heidi Horstmann

doi:10.1682/jrrd.2003.07.0106

Cited by 39 publications

(32 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, voice recognition software requires a high investment in terms of learning time. 17 After 10 min of voice recording, it is necessary to learn the most appropriate manner in which to dictate to the software. For example, based on our clinical experience, it is preferable to formulate the sentence mentally before saying it aloud.…”

Section: Discussionmentioning

confidence: 99%

Text input speed in persons with cervical spinal cord injury

Pouplin

Roche

Vaugier³

et al. 2015

Spinal Cord

View full text Add to dashboard Cite

Study design: This is a prospective clinical study. Objectives: The objectives of this study were to determine text input speed (TIS) in persons with cervical spinal cord injury (SCI) and to study the influence of personal characteristics and type of computer access device on TIS. Setting: This study was conducted in the Rehabilitation Department, Garches, France. Methods: People with cervical SCI were included if their level of injury was between C4 and C8 Asia A or B, and if they were computer users. In addition, able-bodied people were recruited from the hospital staff. Each participant underwent a single evaluation using their usual computer access devices. TIS was evaluated during a 10-min copying task. The relationship between the characteristics of participants with cervical SCI, type of computer access device and TIS were analyzed using a Scheirer-Ray-Hare test (nonparametric test similar to a two-way analysis of variance). Results: Thirty-five participants with cervical SCI and 21 able-bodied people were included. Median TIS of participants with cervical SCI was 9 (6; 14) words per minute (w.p.m.) and of able-bodied participants was 19 (14; 24) w.p.m. (P = 0.001). Median TIS of participants with lesions at or above C5 was 12 (4; 13) w.p.m. and of those with lesions below C5 was 10 (9; 18) w.p.m. (P = 0.38). The Scheirer-Ray-Hare test showed that only the type of computer access device significantly influenced TIS. Surprisingly, none of the person's characteristics, including the level of cervical lesion, affected TIS. Conclusion: This is the first study to analyze TIS in a group of participants with cervical SCI. The results showed that only the type of computer access device influenced TIS.

show abstract

Section: Discussionmentioning

confidence: 99%

Text input speed in persons with cervical spinal cord injury

Pouplin

Roche

Vaugier³

et al. 2015

Spinal Cord

View full text Add to dashboard Cite

show abstract

“…143). Koester (2004) studied participants who had used speech recognition technology for at least six months. The participants were given two text entry tasks to measure speed.…”

Section: Description Of Speech Recognition Software Speech Recognitimentioning

confidence: 99%

“…Eleven of the 18 participants were able to achieve higher text entry rates using speech recognition and were an average of 8.9 words per minute faster than without. Koester (2004) noted that for individuals who typed slower than 15 words per minute, speech recognition improved their text entry rate.…”

Section: Description Of Speech Recognition Software Speech Recognitimentioning

confidence: 99%

“…Recognition accuracy raged from 72% to 94%, averaging 85%. Koester (2004) indicated that participants spent an average of 56% of their text entry time correcting recognition errors, averaging 23 seconds and 1.8 attempts to correct the error. In a survey of the participants, 75% indicated that they found the speed of entry of the speech recognition system to be acceptable.…”

Section: Description Of Speech Recognition Software Speech Recognitimentioning

confidence: 99%

See 1 more Smart Citation

Using Speech Recognition Software to Increase Writing Fluency for Individuals with Physical Disabilities

Garrett

Heller

Fowler

et al. 2011

J Spec Educ Technol

View full text Add to dashboard Cite

Students with physical disabilities often have difficulty with writing fluency, despite the use of various strategies, adaptations, and assistive technology (AT). One possible intervention is the use of speech recognition software, although there is little research on its impact on students with physical disabilities. This study used an alternating treatments design to compare the use of speech recognition software to word processing on first draft writing with students with physical disabilities. Areas examined were fluency, accuracy, type of word errors, recall of intended meaning, and length. The results of this study indicated that fluency and length were greater for all participants with speech recognition compared to word processing, but accuracy was lower using speech recognition.

show abstract

“…In speech systems, error rates have been found to correlate only loosely with satisfaction [16]. According to [17], higher speech recognition accuracy tends to be associated with better general performance (e.g. higher text entry rate), but the correlation, at 0.62, is not as strong as might be expected.…”

mentioning

confidence: 98%

Towards a taxonomy of error-handling strategies in recognition-based multi-modal human–computer interfaces

Bourguet

2006

Signal Processing

View full text Add to dashboard Cite

In this paper, we survey the different types of error-handling strategies that have been described in the literature on recognition-based human-computer interfaces. A wide range of strategies can be found in spoken human-machine dialogues, handwriting systems, and multimodal natural interfaces.We then propose a taxonomy for classifying error-handling strategies that has the following three dimensions: the main actor in the error-handling process (machine versus user), the purpose of the strategy (error prevention, discovery, or correction), and the use of different modalities of interaction. The requirements that different error-handling strategies have on different sets of interaction modalities are also discussed. The main aim of this work is to establish a classification that can serve as a tool for understanding how to develop more efficient and more robust multimodal human-machine interfaces.Keywords: recognition-based technology, multimodal interfaces, error-handling, taxonomy, interaction design, interaction robustness Recognition-based technologyMultimodal interaction refers to interaction with the virtual and physical environment through natural modes of communication such as speech, body gestures, handwriting, graphics, or gaze.Unlike keyboards and mice inputs, natural modes of communication usually are non-deterministic, and have to be "recognised" by a recognition system, before they can be passed on to an application.Recent developments in recognition-based technology (e.g. speech and gesture recognition) have opened a myriad of new possibilities for the design and implementation of multimodal applications.Handwriting recognisers, for example, are being used in personal digital assistants (e.g. Paragon's multilingual PenReader software for Pocket PC devices), and speech recognition has made its way into desktop machines (e.g. IBM's ViaVoice TM speech recognition engines). However, designing and

show abstract

Usage, performance, and satisfaction outcomes for experienced users of automatic speech recognition

Cited by 39 publications

References 11 publications

Text input speed in persons with cervical spinal cord injury

Text input speed in persons with cervical spinal cord injury

Using Speech Recognition Software to Increase Writing Fluency for Individuals with Physical Disabilities

Towards a taxonomy of error-handling strategies in recognition-based multi-modal human–computer interfaces

Contact Info

Product

Resources

About