The Automatic Detection of Speech Disorders in Children: Challenges, Opportunities, and Preliminary Results

Shahin, Mostafa; Zafar, Usman; Ahmed, Beena

doi:10.1109/jstsp.2019.2959393

Cited by 30 publications

(20 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The results are recapitulated for diagnosis of the child. Our proposed approach based on speaker-level representation is compared with methods in which word-level or phone-level error detection is done first on individual test words and subsequently combined to obtain the subject-level decision [11,13,18]. Phone-level detection is implemented based on our previous work in [11].…”

Section: Fusing Phone/word-level Resultsmentioning

confidence: 99%

“…Paralinguistic features defined in the extended Geneva Minimalistic Acoustic Parameter Set (eGeMAPS) represents the overall acoustic characteristics of a speech utterance using statistical functionals [12]. They were successfully applied to detect atypical speech, including disordered speech with phonological and articulation problems [13]. The approach of speaker verification (SV) was also investigated on classifying disordered speech [14][15][16][17].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Detection of Speech Sound Disorder in Child Speech Using Posterior-based Speaker Representations

Ng¹,

Ng²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

This paper presents a macroscopic approach to automatic detection of speech sound disorder (SSD) in child speech. Typically, SSD is manifested by persistent articulation and phonological errors on specific phonemes in the language. The disorder can be detected by focally analyzing the phonemes or the words elicited by the child subject. In the present study, instead of attempting to detect individual phone-and word-level errors, we propose to extract a subject-level representation from a long utterance that is constructed by concatenating multiple test words. The speaker verification approach, and posterior features generated by deep neural network models, are applied to derive various types of holistic representations. A linear classifier is trained to differentiate disordered speech in normal one. On the task of detecting SSD in Cantonese-speaking children, experimental results show that the proposed approach achieves improved detection performance over previous method that requires fusing phone-level detection results. Using articulatory posterior features to derive i-vectors from multiple-word utterances achieves an unweighted average recall of 78.2% and a macro F1 score of 78.0%.

show abstract

Section: Fusing Phone/word-level Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Automatic Detection of Speech Sound Disorder in Child Speech Using Posterior-based Speaker Representations

Ng¹,

Ng²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…human speech recognition ) sind bislang noch nicht ausreichend verfügbar. Aspekte wie Alter, Dialekt, Art und Schweregrad einer Störung erschweren die Umsetzung solcher Datensets zusätzlich 9 10 12 .…”

Section: Sprachverarbeitungstechnologien In Der Logopädie Und Spracht...unclassified

“…Beide Systeme nutzen ASR-Systeme auf Phonemebene, um Sprechfehler bei u. a. phonetisch-phonologischen Störungen oder bei kindlicher Sprechapraxie zu detektieren und rückzumelden. Shahin et al (2020) zeigen in diesem Zusammenhang auf, dass die Reliabilität dieser Analyseverfahren noch nicht ausreichend ist, um in klinischen Anwendungen umgesetzt zu werden 12 .…”

Section: Sprachverarbeitungstechnologien In Der Logopädie Und Spracht...unclassified

“…Kindersprache ist durch höhere Inter- und Intravariabilitäten und mehr noch bei vorliegender Pathologie gekennzeichnet als die von Erwachsenen. Viele ASR-Systeme sind nicht mit Kindersprache modelliert 12 . Weitere Anforderungen liegen hier auch bei der Generierung des automatischen Feedbacks und der nutzer*innenansprechenden Umsetzung in einer digitalen Anwendung vor dem Hintergrund der Motivation.…”

Section: Sprachverarbeitungstechnologien In Der Logopädie Und Spracht...unclassified

See 1 more Smart Citation

Einsatz von Sprachverarbeitungstechnologien in der Logopädie und Sprachtherapie

Tuschen¹

2022

Sprache · Stimme · Gehör

View full text Add to dashboard Cite

show abstract

A Game-Based Smart System Identifying Developmental Speech and Language Disorders in Child Communication: A Protocol Towards Digital Clinical Diagnostic Procedures

Toki

Zakopoulou

Tatsis

et al. 2022

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

The Automatic Detection of Speech Disorders in Children: Challenges, Opportunities, and Preliminary Results

Cited by 30 publications

References 70 publications

Automatic Detection of Speech Sound Disorder in Child Speech Using Posterior-based Speaker Representations

Automatic Detection of Speech Sound Disorder in Child Speech Using Posterior-based Speaker Representations

Einsatz von Sprachverarbeitungstechnologien in der Logopädie und Sprachtherapie

A Game-Based Smart System Identifying Developmental Speech and Language Disorders in Child Communication: A Protocol Towards Digital Clinical Diagnostic Procedures

Contact Info

Product

Resources

About