Truace
Subscribe

Several AI models detected speech-therapist-rated hypernasal speech in 40 children and teens

Study title: Artificial Intelligence-Based Hypernasality Diagnosis Using CAPS-A-AM Rated Speech Samples in Pediatric Velopharyngeal Dysfunction

ObjectivePerceptual evaluation by speech-language pathologists (SLPs) is essential for initial evaluation of velopharyngeal dysfunction (VPD). Machine learning (ML) offers a promising avenue for developing accessible speech assessment tools when SLP expertise is limited.

Read the study abstract

ObjectivePerceptual evaluation by speech-language pathologists (SLPs) is essential for initial evaluation of velopharyngeal dysfunction (VPD). Machine learning (ML) offers a promising avenue for developing accessible speech assessment tools when SLP expertise is limited. We aimed to develop a workflow and preliminary algorithm for AI-based hypernasality detection based on the Cleft Audit Protocol for Speech-Augmented-Americleft Modification (CAPS-A-AM), a standardized framework for auditory perceptual speech ass…

By the Truvace desk2 min read1 sourceEvidence: Moderate · 64/100 — Controlled or validated comparison · n = 40 · 1 independent sourcePeer-reviewedTRV-2026-1140· cite & verify
Artificial Intelligence-Based Hypernasality Diagnosis Using CAPS-A-AM Rated Speech Samples in Pediatric Velopharyngeal Dysfunction
Hospital Universitari Doctor Peset, València 10 by 19Tarrestnom65. CC BY-SA 4.0 · https://creativecommons.org/licenses/by-sa/4.0

In brief

We aimed to develop a workflow and preliminary algorithm for AI-based hypernasality detection based on the Cleft Audit Protocol for Speech-Augmented-Americleft Modification (CAPS-A-AM), a standardized framework for auditory perceptual speech assessment.DesignIn this prospective, single-center study, speech samples were collected during SLP-guided evaluation, with consensus CAPS-A-AM ratings established. Three ML approaches were evaluated: logistic regression (LR), Convolutional Neural Network (CNN) Attention-Multiple Instance Learning (MIL) (EfficientNet-V2-S), and a CNN-Extreme Gradient Boosting Hybrid (XGBoost).Patients/ParticipantsForty pediatric participants aged 2 to 17, including individuals with VPD, conditions associated with VPD, and healthy participants.Main Outcome Measure(s)Model performance was tested in binary hypernasality classification compared to SLP consensus at two CAPS-A-AM thresholds: absent (0) versus any hypernasality (1-4) and absent/borderline (0-1) versus mild-to-severe hypernasality (2-4).ResultsMultiple independent modeling approaches were able to detect clinically rated hypernasality.

Main points

  1. ObjectivePerceptual evaluation by speech-language pathologists (SLPs) is essential for initial evaluation of velopharyngeal dysfunction (VPD).
  2. Machine learning (ML) offers a promising avenue for developing accessible speech assessment tools when SLP expertise is limited.
  3. We aimed to develop a workflow and preliminary algorithm for AI-based hypernasality detection based on the Cleft Audit Protocol for Speech-Augmented-Americleft Modification (CAPS-A-AM), a standardized framework for auditory perceptual speech assessment.DesignIn this prospective, single-center study, speech samples were collected during SLP-guided evaluation, with consensus CAPS-A-AM ratings established.

The gain

Several ML models detected speech-therapist-rated hypernasality in 40 children and teens, suggesting accessible assessment tools where SLP expertise is limited.

The rundown

ObjectivePerceptual evaluation by speech-language pathologists (SLPs) is essential for initial evaluation of velopharyngeal dysfunction (VPD). Machine learning (ML) offers a promising avenue for developing accessible speech assessment tools when SLP expertise is limited.

We aimed to develop a workflow and preliminary algorithm for AI-based hypernasality detection based on the Cleft Audit Protocol for Speech-Augmented-Americleft Modification (CAPS-A-AM), a standardized framework for auditory perceptual speech assessment.DesignIn this prospective, single-center study, speech samples were collected during SLP-guided evaluation, with consensus CAPS-A-AM ratings established. Mel spectrograms for high vowels (/i/ and /u/) were generated from sustained vowels, isolated words, and sentences for model development.

Sources

  1. Peer-reviewedThe Cleft Palate Craniofacial Journal2026-09-18

The debate