The DOI matches its Crossref record; 98 of the 102 references it cites were found in a registry or an index.
The Automatic Detection of Speech Disorders in Children: Challenges, Opportunities, and Preliminary Results
Abstract
Given the limited accessibility to Speech and Language Pathologists (SLPs) children in need often have, pediatric Computer-Aided Speech Therapy (CAST) tools can play an important role in the early diagnosis and treatment of speech disorders. However, various challenges impede the implementation of accurate automated analysis of speech disorders in children. In this article, we first discuss three key challenges in processing child disordered speech: 1) the unreliability of low-level annotation and scarcity of speech corpora, 2) speaker diarization of therapy sessions and 3) inaccurate children's acoustic models. We next explore opportunities to overcome some of these challenges. First, we investigate the effectiveness of high-level paralinguistic features in disordered speech detection to reduce the dependency on annotated data. A binary classifier trained using paralinguistic features extracted from both typically developing children and those suffering from Speech Sound Disorders (SSD) achieved 87% subject-level classification accuracy. Second, we tackle the speech disorder detection problem as an anomaly detection problem where models are trained merely on typically developing speech, reducing the need for disordered training data. A phoneme-levelF1 score of 0.77 was obtained from an anomaly detection-based system trained on speech attribute features to classify between typical and atypical phoneme pronunciations of children with speech disorder. Finally, we test the efficiency of an x-vector based speaker diarization technique in pediatric therapy sessions. The method successfully distinguished between therapist and child speech with a Diarization Error Rate (DER) of 10%.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“First, and perhaps most critically, there has not been enough publicly available audio or video examples of speech and language disorders to develop AI systems that work well for children or adults with these types of disorders (e.g., Benway et al., 2023;Berisha et al., 2021;Shahin et al., 2020).”
From Equipping Speech-Language Clinicians for the Critical Appraisal of an Artificial Intelligence–Driven, Evidence-Based Future (2025) · cites this paper as Shahin et al., 2020
In the citing paper
“Children’s speech varies significantly across individuals and evolves rapidly, making it difficult for AI models, particularly those trained on adult data, to accurately analyze and detect impairments in younger users. 12”
From Artificial intelligence (AI)-driven technologies for managing pediatric speech and language therapy: A scoping review (2025) · cites this paper as [12]
In the citing paper
“child speech exhibits greater inter- and intra-speaker variability compared to adult speech, posing additional challenges for processing and analysis. 12”
From Artificial intelligence (AI)-driven technologies for managing pediatric speech and language therapy: A scoping review (2025) · cites this paper as [12]
In the citing paper
“As mentioned before, one of the main challenges in working with children’s speech data is the scarcity of available corpora. 12”
From Artificial intelligence (AI)-driven technologies for managing pediatric speech and language therapy: A scoping review (2025) · cites this paper as [12]
In the citing paper
“Another commonly mentioned challenge is the low quality of annotated data for children, primarily due to the wide variability in pronunciations among younger speakers. 12”
From Artificial intelligence (AI)-driven technologies for managing pediatric speech and language therapy: A scoping review (2025) · cites this paper as [12]
Citations
Cites
Gene selection for cancer classification using support vector machines
Guyon, I., Weston, J., Barnhill, S., & Vapnik, V. (2002) · Machine Learning · doi:10.1023/a:1012487302797 · Cited by 9,954 · cited 1×
“nation (RFE) feature selectionmethod [100] to identify the most discriminative parameters.”
BackgroundFront-End Factor Analysis for Speaker Verification
Dehak, N., Kenny, P. J., Dehak, R., Dumouchel, P., & Ouellet, P. (2011) · IEEE Transactions on Audio, Speech, and Language Processing · doi:10.1109/tasl.2010.2064307 · Cited by 3,549
X-Vectors: Robust DNN Embeddings for Speaker Recognition
Snyder, D., Garcia-Romero, D., Sell, G., Povey, D., & Khudanpur, S. (2018) · 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2018.8461375 · Cited by 2,620 · cited 3×
“These settings are adopted to match the configurations of the pre-trained model as described in [75].”
MethodSupport Vector Method for Novelty Detection
Schölkopf, B., Williamson, R. C., Smola, A. J., Shawe-Taylor, J. S., & Platt, J. C. (1999) · Cited by 2,040
The Geneva Minimalistic Acoustic Parameter Set (GeMAPS) for Voice Research and Affective Computing
Eyben, F., Scherer, K. R., Schuller, B. W., Sundberg, J., Andre, E., Busso, C., Devillers, L. Y., Epps, J., Laukka, P., Narayanan, S. S., et al. (2016) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2015.2457417 · Cited by 1,818 · cited 4×
“Here we extracted features in the minimalistic acoustic parameter sets (GeMAPS and eGeMAPS) which include the pitch, jitter, formant frequencies, shimmer, loudness, spectral energies, first four MFCCs, and mean and standard deviation of voiced/unvoiced regions (see [95] for complete list).”
BackgroundMethodInfluentialDARPA TIMIT: acoustic-phonetic continuous speech corpus CD-ROM, NIST speech disc 1-1.1
Garofolo, J. S., Lamel, L. F., Fisher, W. M., Fiscus, J. G., Pallett, D. S., & Dahlgren, N. L. (1993) · doi:10.6028/nist.ir.4930 · Cited by 1,267 · cited 1×
“1) TIMIT Corpus [110]: This is a standard phonetically-rich speech corpus designed for the evaluation of acoustic modeling.”
BackgroundRecent developments in openSMILE, the munich open-source multimedia feature extractor
Eyben, F., Weninger, F., Gross, F., & Schuller, B. (2013) · Proceedings of the 21st ACM international conference on Multimedia · doi:10.1145/2502081.2502224 · Cited by 1,241 · cited 1×
“3 [99] was used for feature extraction.”
The AMI Meeting Corpus: A Pre-announcement
Carletta, J., Ashby, S., Bourban, S., Flynn, M., Guillemot, M., Hain, T., Kadlec, J., Karaiskos, V., Kraaij, W., Kronenthal, M., et al. (2006) · Lecture Notes in Computer Science · doi:10.1007/11677482_3 · Cited by 908 · cited 3×
“While annotating the data, we followed the protocol mentioned in [111].”
BackgroundMethodInfluentialSchuller, B., Steidl, S., Batliner, A., Vinciarelli, A., Scherer, K., Ringeval, F., Chetouani, M., Weninger, F., Eyben, F., Marchi, E., et al. (2013) · Interspeech 2013 · doi:10.21437/interspeech.2013-56 · Cited by 731 · cited 1×
“1) Feature Extraction: The most commonly used standard paralinguistic parameter sets are the large-scale Interspeech 2013 Computational Paralinguistic ChallengE (ComParE) (6,373 parameters) [98], the Geneva Minimalistic Acoustic Parameter Set (GeMAPS) (62 parameters) and its extended version eGeMAPS (88 parameters) [9…”
Speaker Diarization: A Review of Recent Research
Anguera Miro, X., Bozonnet, S., Evans, N., Fredouille, C., Friedland, G., & Vinyals, O. (2012) · IEEE Transactions on Audio, Speech, and Language Processing · doi:10.1109/tasl.2011.2125954 · Cited by 669 · cited 1×
“using factor analysis techniques and shown to performwell [73].”
Method
Research works printed but not linked: 7
- chee, 0, Overview of automatic stuttering recognition system, Proc Int Conf Man-Mach Syst
- al-barhamtoshy, 2014, Speak correct: Phonetic editor approach, Life Sci, 11, 626
- vikramc, 0, Estimation of hypernasality scores from cleft lip and palate speech, Proc INTERSPEECH, 1701
- 2007, Childhood Apraxia of Speech Position Statement
- rvachew, 2010, Speech perception intervention, Interventions for Speech Sound Disorders in Children, 295
- chiat, 1994, From lexical access to lexical output: What is the problem for children with impaired phonology, First Second Lang Pathol, 107
- eskenazi, 1997, The CMU Kids Speech Corpus
Cited by
Informing Age-Appropriate AI: Examining Principles and Practices of AI for Children
Wang, G., Zhao, J., Van Kleek, M., & Shadbolt, N. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3502057 · Cited by 76
Dysarthric-speech detection using transfer learning with convolutional neural networks
Sekhar, S. R. M., Kashyap, G., Bhansali, A., Azhagesan, A. A. A., & Singh, K. (2021) · ICT Express · doi:10.1016/j.icte.2021.07.004 · Cited by 53
Beccaluva, E. A., Catania, F., Arosio, F., & Garzotto, F. (2024) · Human–Computer Interaction · doi:10.1080/07370024.2023.2242837 · Cited by 24
“…set instead of a larger or different set as eGeMAPS offers some advantages: it reduces the possibility of overfitting our models to the training data; moreover, the feature set has already been shown as promising for assessing linguistic disorders (Shahin et al., 2019, 2020; Xue et al., 2019).”
BackgroundJothi, K. R., Sivaraju, S. S., & Yawalkar, P. J. (2020) · International Conference on Electronics, Communication and Aerospace Technology (ICECA) · doi:10.1109/iceca49313.2020.9297591 · Cited by 23
“2020), focused on outstanding approach used to find the 3 common pronunciation errors made by children [31].”
BackgroundMethodDeveloping children's ASR system under low-resource conditions using end-to-end architecture
Ankita, & Shahnawazuddin, S. (2024) · Digital Signal Processing · doi:10.1016/j.dsp.2024.104385 · Cited by 21
Metadata
- Authors
- Shahin, M., Zafar, U., & Ahmed, B.
- Affiliations
- UNSW Sydney (AU)
- Texas A&M University at Qatar (QA)
- Venue
- IEEE Journal of Selected Topics in Signal Processing
- Published
- 2020-02
- Volume
- 14
- Issue
- 2
- Pages
- 400-412
- ISSN
- 1932-4553 (ISSN-L)
- 1941-0484
- OpenAlex
- W3016223211
- Cited by
- 62
- References
- 102
- Citations by year
- 2026: 9 · 2025: 14 · 2024: 14 · 2023: 7 · 2022: 10 · 2021: 3 · 2020: 5
- FWCI
- 2.08
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Journal of Selected Topics in Signal Processing (publishedVersion)
- Funders
- NPRP (8-293-2-124)
- Qatar National Research Fund
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Social Sciences › Psychology › Developmental and Educational Psychology › Language Development and Disorders
- Health Sciences › Health Professions › Speech and Hearing › Voice and Speech Disorders
- Keywords
- children, speech sound disorders, paralinguistic features, anomaly detection, acoustic modeling, phoneme classification
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: The Automatic Detection of Speech Disorders in Children: Challenges, Opportunities, and Preliminary Results. https://app.cochat.ai/papers/10.1109/jstsp.2019.2959393
- The paper
- Shahin, M., Zafar, U., & Ahmed, B. (2020). The Automatic Detection of Speech Disorders in Children: Challenges, Opportunities, and Preliminary Results. IEEE Journal of Selected Topics in Signal Processing. https://doi.org/10.1109/jstsp.2019.2959393
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.