Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jun 28, 2026

Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis
05:48

Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis

Published on: August 9, 2024

Automatic recognition of pathological phoneme production.

Robert Wielgat1, Tomasz P Zieliński, Tomasz Woźniak

  • 1Department of Technology, Higher State Vocational School in Tarnów, Tarnów, Poland. rwielgat@poczta.onet.pl

Folia Phoniatrica Et Logopaedica : Official Organ of the International Association of Logopedics and Phoniatrics (IALP)
|November 18, 2008
PubMed
Summary

This study introduces an automatic system for recognizing pathological phoneme pronunciation in children with speech disorders. Human Factor Cepstral Coefficients (HFCC) outperformed Mel-Frequency Cepstral Coefficients (MFCC) in detecting speech errors.

Related Concept Videos

Prosopagnosia01:24

Prosopagnosia

Prosopagnosia, also known as face blindness, is the inability to recognize faces. In severe cases, individuals with prosopagnosia may not recognize close family members, including parents and spouses, by their faces. For instance, someone with prosopagnosia might walk past their child in a crowd, only realizing their mistake upon noticing their child's distinctive backpack or favorite jacket. Prosopagnosia specifically impairs facial recognition, while the recognition of other objects or...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Extremely High Excitonic g Factors in 2D Crystals by Alloy-Induced Admixing of Band States.

Physical review letters·2026
Same author

Experimental Evaluation of 5G NR OFDM-Based Passive Radar Exploiting Reference, Control, and User Data.

Sensors (Basel, Switzerland)·2026
Same author

Developing acoustic field distribution analysis tools for noninvasive assessment of laterality and nasality in disordered and typical pronunciation.

Clinical linguistics & phonetics·2025
Same author

Analysis of Surface EMG Signals to Control of a Bionic Hand Prototype with Its Implementation.

Sensors (Basel, Switzerland)·2025
Same author

Integrated Sensing and Communication Using Random Padded OTFS with Reduced Interferences.

Sensors (Basel, Switzerland)·2025
Same author

Remote Radio Frequency Sensing Based on 5G New Radio Positioning Reference Signals.

Sensors (Basel, Switzerland)·2025

Area of Science:

  • Speech-language pathology
  • Computational linguistics
  • Biomedical engineering

Background:

  • Accurate diagnosis and therapy of pathological phoneme pronunciation are crucial in modern speech therapy.
  • Automatic recognition systems can enhance the efficiency of speech disorder diagnosis and therapy.
  • Phoneme substitution disorders are a common focus in speech therapy.

Purpose of the Study:

  • To develop and evaluate an automatic recognition system for pathological phoneme pronunciation, specifically focusing on phoneme substitution disorders.
  • To compare the effectiveness of Human Factor Cepstral Coefficients (HFCC) against standard Mel-Frequency Cepstral Coefficients (MFCC) for feature extraction.
  • To compare the performance of Dynamic Time Warping (DTW) and Hidden Markov Models (HMM) as classifiers for detecting speech sound substitutions.

Related Experiment Videos

Last Updated: Jun 28, 2026

Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis
05:48

Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis

Published on: August 9, 2024

Main Methods:

  • Speech samples from Polish children with speech impairments and individuals imitating speech disorders were analyzed.
  • Phoneme substitutions were embedded in Polish carrier words.
  • Human Factor Cepstral Coefficients (HFCC) and Mel-Frequency Cepstral Coefficients (MFCC) were used as feature vectors.
  • Dynamic Time Warping (DTW) and Hidden Markov Models (HMM) were employed as classifiers, utilizing both whole-word and phoneme-based models.

Main Results:

  • Human Factor Cepstral Coefficients (HFCC) demonstrated superior performance compared to Mel-Frequency Cepstral Coefficients (MFCC).
  • Dynamic Time Warping (DTW) methods, particularly a modified phoneme-based DTW classifier, yielded slightly better results than Hidden Markov Models (HMM).
  • The detection of substitution in pairs showed very promising results.

Conclusions:

  • The study confirms the superiority of HFCC features for pathological phoneme pronunciation recognition.
  • Modified phoneme-based DTW classifiers offer a promising approach for detecting speech sound substitutions.
  • The developed methods have the potential for integration into computer-assisted speech therapy systems, although further research is needed for specific substitution types.