Fluency Bank: A new resource for fluency research and practice

Ratner, Nan Bernstein; MacWhinney, Brian

doi:10.1016/j.jfludis.2018.03.002

Cited by 63 publications

(30 citation statements)

References 102 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DL saves feature engineering costs by automatically generating relevant features, however require substantial amounts of annotated data. Most stuttering identification studies so far are based on in-house datsets [3,30,33,71,72] with limited speakers. In stuttering domain, there is a lack of datasets and several stuttering datasets that have been collected so far are discussed below: .…”

Section: Datasets For Stuttering Detection Researchmentioning

confidence: 99%

“…FluencyBank. This is a shared database for the study of fluency development which has been developed by Nan Bernstein Ratner (University of Maryland) and Brian MacWhinney (Carnegie Mellon University) [3]. The platform proposes audio and video files with transcriptions of adults and children who stutter.…”

Section: Torgo This Was Developed By a Collaboration Between Departme...mentioning

confidence: 99%

“…Speech disorders or speech impairments are communication disorders in which a person has difficulties in creating and forming the normal speech sounds required to communicate with others [1,2]. These disorders can take the form of dysarthria, apraxia, stuttering, cluttering, lisping, and so on [1][2][3][4][5].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Machine Learning for Stuttering Identification: Review, Challenges and Future Directions

Sheikh¹,

Sahidullah²,

Hirsch³

et al. 2021

Preprint

View full text Add to dashboard Cite

Stuttering is a speech disorder during which the flow of speech is interrupted by involuntary pauses and repetition of sounds. Stuttering identification is an interesting interdisciplinary domain research problem which involves pathology, psychology, acoustics, and signal processing that makes it hard and complicated to detect. Recent developments in machine and deep learning have dramatically revolutionized speech domain, however minimal attention has been given to stuttering identification. This work fills the gap by trying to bring researchers together from interdisciplinary fields. In this paper, we review comprehensively acoustic features, statistical and deep learning based stuttering/disfluency classification methods. We also present several challenges and possible future directions.

show abstract

Section: Datasets For Stuttering Detection Researchmentioning

confidence: 99%

Section: Torgo This Was Developed By a Collaboration Between Departme...mentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning for Stuttering Identification: Review, Challenges and Future Directions

Sheikh¹,

Sahidullah²,

Hirsch³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…These include the Developmental Sentence Score (DSS, Lee, 1974) and the Index of Productive Syntax (IPSyn, Scarborough, 1990) for child language, as wells as the Northwestern Narrative Language Analysis (NNLA, Thompson et al, 1995), Quantitative Production Analysis (QPA, Rochon, Saffran, Berndt, & Schwartz, 2000), and Computerized Propositional Idea Density Rater (CPIDR, Brown, Snodgrass, Kemper, Herman, & Covington, 2008) for aphasia. Both the basic measures and the more complex profile measures are then packaged together into either the KIDEVAL system for child language, the EVAL system for adult language analysis, or the FLUCALC system for stuttering (Bernstein Ratner & MacWhinney, 2018). Using these systems, a researcher or clinician can summarize the data for a group or a single participant and can compare a single participant with reference groups from the TalkBank database.…”

Section: Talkbank Principlesmentioning

confidence: 99%

Understanding spoken language through TalkBank

MacWhinney

2018

Behav Res

Self Cite

View full text Add to dashboard Cite

Ongoing advances in computer technology have opened up a deluge of new datasets for understanding human behavior (Goldstone & Lupyan, 2016). Many of these datasets provide information on the use of written language. However, data on naturally occurring spoken-language conversations are much more difficult to obtain. A major exception to this is the TalkBank system, which provides online multimedia data for 14 types of spoken-language data: language in aphasia, child language, stuttering, child phonology, autism spectrum disorder, bilingualism, Conversation Analysis, classroom discourse, dementia, right hemisphere damage, Danish conversation, second language learning, traumatic brain injury, and daylong recordings in the home. The present report reviews these resources and describes the ways they are being used to further our understanding of human language and communication.

show abstract

“…Again, we must reiterate that we had very little power to detect these effects given a sample size of 50 children. The fact that we did suggests that future work examining language growth with a larger sample may yield stronger effects, though we hold off on speculating further until such data are available, perhaps in future years by combining research data from multiple sites, which is the goal of Fluency Bank (Bernstein Ratner & MacWhinney, 2018).…”

mentioning

confidence: 94%