Comparing judgments of stuttering made by students, clinicians, and highly experienced judges

Brundage, Shelley B.; Bothe, Anne K.; Lengeling, Amy N.; Evans, Janice Perry

doi:10.1016/j.jfludis.2006.07.002

Cited by 34 publications

(39 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They also noted that training judges could significantly improve interjudge agreement of discrimination between stuttered and non-stuttered speech and that, independent of training, judges with relatively high intrajudge agreement also showed relatively higher interjudge agreement (Ingham, Cordes, & Finn, 1993;Ingham, Cordes, & Gow, 1993). Interestingly, Brundage, Bothe, Lengeling, and Evans (2006) reported findings of high intrajudge and interjudge agreement coexisting with low accuracy in students' judgments of stuttering and that similar problems were also evident in judgments made by practicing clinicians. Although the present study found high intrajudge and interjudge measurement/agreement with high accuracy when using highly experienced judges, the importance of accuracy as well as reliability of measurement of stuttering cannot be overstated and clearly remains a fruitful grounds for continued research.…”

Section: Direct Observation and Reliabilitymentioning

confidence: 98%

Characteristics of stuttering-like disfluencies in Dutch-speaking children

Boey

Wuyts

Heyning

et al. 2007

Journal of Fluency Disorders

View full text Add to dashboard Cite

Section: Direct Observation and Reliabilitymentioning

confidence: 98%

Characteristics of stuttering-like disfluencies in Dutch-speaking children

Boey

Wuyts

Heyning

et al. 2007

Journal of Fluency Disorders

View full text Add to dashboard Cite

“…This measurement is usually conducted by counting the number of stuttering events in the child's speech. This process is extremely dependent on the clinician's experience [8]. In another approach, the clinician transcribes a recorded session and classifies each spoken term into one of several normal, disfluent This project is part of a CloudCAST project.…”

Section: Introductionmentioning

confidence: 99%

Automatic recognition of children's read speech for stuttering application

Alharbi¹,

Simons²,

Brumfitt³

et al. 2017

6th Workshop on Child Computer Interaction (WOCCI 2017)

View full text Add to dashboard Cite

Stuttering is a common speech disfluency that may persist into adulthood if not treated in its early stages. Techniques from spoken language understanding may be applied to provide automated diagnoses of stuttering from voice recordings; however, there are several difficulties, including the lack of training data involving young children and the high dimensionality of these data. This study investigates how automatic speech recognition (ASR) could help clinicians by providing a tool that automatically recognises stuttering events and provides a useful written transcription of what was said. In addition, to enhance the performance of ASR and to alleviate the lack of stuttering data, this study examines the effect of augmenting the language model with artificially generated data. The performance of the ASR tool with and without language model augmentation is compared. Following language model augmentation, the ASR tool's performance improved recall from 38% to 62.2% and precision from 56.58% to 71%. When mis-recognised events are more coarsely classified as stuttering/ non-stuttering events, the performance improves up to 73% in recall and 84% in precision. Although the obtained results are not perfect, they map to fairly robust stutter/ non-stutter decision boundaries.

show abstract

“…In that study ten undergraduate students accurately identified (before training) only 30% of intervals that authorities on stuttering had agreed were stuttered. Also relevant is a recent study by Brundage et al (2006) who reported that graduate students (n541) accurately identified a mean 37.5% of Agreed Stuttered intervals from the corpus used within the study of Cordes and Ingham (1996). In addition, Brundage et al (2006) reported that 31 clinicians identified correctly a mean 51.6% of the Agreed Stuttered intervals within their study.…”

Section: Accuracy Of Parents' Judgementsmentioning

confidence: 98%