Motion does matter: an examination of speech-based text entry on the move

Price, James E.; Lin, Min; Feng, Jinjuan; Goldman, Rich; Sears, Andrew; Jacko, A.

doi:10.1007/s10209-005-0006-8

Cited by 15 publications

(6 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These results are consistent with what is known about how movement affects respiration. Vigorous motor activities, like running, speed up breathing cycles (Wasserman et al, 1973; Bramble and Carrier, 1983), resulting in articulation deficits (Sundberg et al, 1991; Price et al, 2006; Baker et al, 2008; Orlikoff, 2008). The finding that calls produced during movement were shorter and noisier indicates that very young marmosets lacked adequate respiratory power (Zhang and Ghazanfar, 2018).…”

Section: Discussionmentioning

confidence: 99%

Vocal and locomotor coordination develops in association with the autonomic nervous system

Gustison

Borjon

Takahashi

et al. 2019

eLife

View full text Add to dashboard Cite

In adult animals, movement and vocalizations are coordinated, sometimes facilitating, and at other times inhibiting, each other. What is missing is how these different domains of motor control become coordinated over the course of development. We investigated how postural-locomotor behaviors may influence vocal development, and the role played by physiological arousal during their interactions. Using infant marmoset monkeys, we densely sampled vocal, postural and locomotor behaviors and estimated arousal fluctuations from electrocardiographic measures of heart rate. We found that vocalizations matured sooner than postural and locomotor skills, and that vocal-locomotor coordination improved with age and during elevated arousal levels. These results suggest that postural-locomotor maturity is not required for vocal development to occur, and that infants gradually improve coordination between vocalizations and body movement through a process that may be facilitated by arousal level changes.

show abstract

Section: Discussionmentioning

confidence: 99%

Vocal and locomotor coordination develops in association with the autonomic nervous system

Gustison

Borjon

Takahashi

et al. 2019

eLife

View full text Add to dashboard Cite

show abstract

“…Note that enrollment refers to the process of reading predefined training material which allows the speech recognition engine to develop a model of how an individual speaks. Therefore, it would seem intuitive that completion of the enrollment process under the same conditions as would be experienced during actual usage should prove beneficial, but contradictory results have been reported (Price et al, 2006). The current research builds on this previous work by examining the effect of enrollment and task conditions on text entry accuracy and efficiency in more detail.…”

Section: Introductionmentioning

confidence: 86%

“…The complete results are reported elsewhere (Price et al, 2006) but are summarized here as they motivated the current study. Thirty-two participants with no prior ASR experience used a speaker-dependent ASR system to complete composition-oriented tasks while they were walking on a treadmill or while they were seated.…”

Section: Literature Reviewmentioning

confidence: 95%

“…The current research project was undertaken with this goal in mind and builds on an earlier study investigating the use of speech recognition for data entry on mobile devices (Price et al, 2006). Results of this earlier study suggested that the conditions an individual experienced while completing the enrollment process as well as the conditions experienced during experimental trials can both affect text entry accuracy and efficiency.…”

Section: Introductionmentioning

confidence: 96%

See 1 more Smart Citation

Nomadic Speech-Based Text Entry: A Decision Model Strategy for Improved Speech to Text Processing

Price¹,

Lin²,

Feng³

et al. 2009

International Journal of Human-Computer Interaction

Self Cite

View full text Add to dashboard Cite

Speech text entry can be problematic during ideal dictation conditions, but difficulties are magnified when external conditions deteriorate. Motion during speech is an extraordinary condition that might have detrimental effects on automatic speech recognition. This research examined speech text entry while mobile. Speech enrollment profiles were created by participants in both a seated and walking environment. Dictation tasks were also completed in both the seated and walking conditions. Although results from an earlier study suggested that completing the enrollment process under more challenging conditions may lead to improved recognition accuracy under both challenging and less challenging conditions, the current study provided contradictory results. A detailed review of error rates confirmed that some participants minimized errors by enrolling under more challenging conditions while others benefited by enrolling under less challenging conditions. Still others minimized errors when different enrollment models were used under the opposing condition. Leveraging these insights, we developed a decision model to minimize recognition error rates regardless of the conditions experienced while completing dictation tasks. When applying the model to existing data, error rates were reduced significantly but additional research is necessary to effectively validate the proposed solution.

show abstract

“…When taking speech recognition mobile, a question arises whether it is worth recording adaptation data in a mobile rather than a desktop setting. Price and colleagues [21] investigated this by having half of their participants record adaptation data while walking on a noisy treadmill, while the other half recorded data while seated in an office (with simulated treadmill noise playing). While not statistically significant, they found that users who had performed adaptation while on the treadmill had a lower word error rate (WER) both when tested on the treadmill and when seated.…”

Section: Speaker Adaptation Environmentmentioning

confidence: 99%

Parakeet

Vertanen

Kristensson

2009

Proceedings of the 14th International Conference on Intelligent User Interfaces

View full text Add to dashboard Cite

We present Parakeet, a system for continuous speech recognition on mobile touch-screen devices. The design of Parakeet was guided by computational experiments and validated by a user study. Participants had an average text entry rate of 18 words-per-minute (WPM) while seated indoors and 13 WPM while walking outdoors. In an expert pilot study, we found that speech recognition has the potential to be a highly competitive mobile text entry method, particularly in an actual mobile setting where users are walking around while entering text.

show abstract

Motion does matter: an examination of speech-based text entry on the move

Cited by 15 publications

References 38 publications

Vocal and locomotor coordination develops in association with the autonomic nervous system

Vocal and locomotor coordination develops in association with the autonomic nervous system

Nomadic Speech-Based Text Entry: A Decision Model Strategy for Improved Speech to Text Processing

Parakeet

Contact Info

Product

Resources

About