Automatic detection of articulation disorders in children with cleft lip and palate.

  title={Automatic detection of articulation disorders in children with cleft lip and palate.},
  author={Andreas K. Maier and Florian H{\"o}nig and Tobias Bocklet and Elmar N{\"o}th and Florian Stelzle and Emeka Nkenke and Maria Schuster},
  journal={The Journal of the Acoustical Society of America},
  volume={126 5},
Speech of children with cleft lip and palate (CLP) is sometimes still disordered even after adequate surgical and nonsurgical therapies. Such speech shows complex articulation disorders, which are usually assessed perceptually, consuming time and manpower. Hence, there is a need for an easy to apply and reliable automatic method. To create a reference for an automatic system, speech data of 58 children with CLP were assessed perceptually by experienced speech therapists for characteristic… 

Figures and Tables from this paper

Automatic phoneme analysis in children with Cleft Lip and Palate

This work proposes two different automatic systems focusing on modeling the articulatory space of a speaker and shows that the fMLLR-based system is able to achieve automatic phoneme evaluation results that are in the same range as perceptual inter-rater-agreements.

Automatic detection of consonant omission in cleft palate speech

The classification between voiced initials and finals is a difficulty in Mandarin speech processing researches, and this work proposes a time-domain waveform difference analysis method to address this difficulty.

Analysis of Feature Extraction Methods for Distinguishing the Speech of Cleft Palate Patients

An analysis of feature extraction methods used for distinguishing the speech of patients with cleft palates and people with normal palates concluded that the MFCC method is generally the most effective way to identify speech distortions.

Automatic evaluation of resonance and articulation disorders in cleft palate speech

The automatic hypernasality grading algorithm is proposed to classify four levels ofhypernasality: normal, mild, moderate and severe and the algorithms of automatic consonant omission and replacement location are proposed to evaluate the speech intelligibility of CP speech.

Automatic Evaluation of Hypernasality and Consonant Misarticulation in Cleft Palate Speech

In this work, automatic classification of hypernasality levels and detection of consonant omission methods are proposed and an effective classification algorithm is proposed through analyzing the acoustic characteristics of initial consonants and finals.

Objective assessment of cleft lip and palate speech intelligibility using articulation and hypernasality measures.

This work proposes an objective measure of sentence-level intelligibility by combining the information of articulation deficits and hypernasality, and shows a significant correlation between the predicted and perceptual intelligibility scores.

Automatic Identification of Articulation Disorders for Arabic Children Speakers

Automatic identification of articulation disorders in children’s speech is very important for the diagnosis and monitoring of speech therapy. In this work, acoustic features (MFCC) have been used

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

This article investigates the effectiveness of high-level paralinguistic features in disordered speech detection to reduce the dependency on annotated data and tackles 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.

Automatic Identification of Speech Disorders for Arabic Children Speakers

Abstract—Automatic identification of speech disorders in children’s speech is very important for the diagnosis and monitoring of speech therapy. In this work, acoustic features (MFCC) have been used



Intelligibility of Children with Cleft Lip and Palate: Evaluation by Speech Recognition Techniques

It is shown that automatic speech recognition serves as a good means to objectify and quantify global speech outcome of children with CLP.

Automatic evaluation of characteristic speech disorders in children with cleft lip and palate

A new technical procedure for themeasurement and evaluation of specic speech disorders and compare the results obtained with subjective ratings of an expe-rienced speech therapist is presented.

Fully Automatic Assessment of Speech of Children with Cleft Lip and Palate

An automatic evaluation system that assesses speech, based on the result of an automatic speech recognizer, is created that complied with experts’ rating of intelligibility of children with CLP.

Evaluation of Speech Disorders in Children with Cleft Lip and Palate

These two subjective methods of evaluation are recommended because of their high reliability with experienced raters and suggest that “experience” is an essential criterion in determining the structural quality of the morphological and functional assessment of typical speech pathologies in children with cleft lip and palate.

Effect of Cleft Type on Overall Speech Intelligibility and Resonance

The findings of the present study show no statistically significant differences for nasalance values, nasality and overall speech intelligibility between the UCLP and BCLP children.

Automatic Speech Recognition Systems for the Evaluation of Voice and Speech Disorders in Head and Neck Cancer

Intelligibility was quantified by speech recognition on recordings of a standard text read by 41 German laryngectomized patients with cancer of the larynx or hypopharynx and 49 German patients who had suffered from oral cancer.

Speech in unilateral and bilateral cleft palate patients from Stockholm.

All cleft patients were found to have poorer speech in spite of considerable speech therapy and complementary surgical treatment, which has resulted in a change in the Stockholm approach toward earlier palatal surgery, tailor-made pharyngeal flap operations, and earlier parental information and treatment of articulatory deviations.

Towards robust automatic evaluation of pathologic telephone speech

This work investigates the evaluation of the intelligibility of speech by means of automatic speech recognition and proposes a combination of two speech recognizers that results in consistent improvements in the correlation between the automatic evaluation and the ratings by human experts.

Recent advances in hypernasal speech detection using the nonlinear Teager energy operator

The results show that the presence of hypernasality in speech can be reliably detected (94.7%) using the proposed classification algorithm and the algorithm was evaluated using native English speakers producing front and mid-vowels.