Cleft Palate Speech Research Articles

Automatic hypernasality grade assessment in cleft palate speech based on the spectral envelope method.

Due to velopharyngeal incompetence, airflow overflows from the oral cavity to the nasal cavity, which results in hypernasality. Hypernasality greatly reduces speech intelligibility and affects the daily communication of patients with cleft palate. Accurate assessment of hypernasality grades can provide assisted diagnosis for speech-language pathologists (SLPs) in clinical settings. Utilizing a support vector machine (SVM), this paper classifies speech recordings into four grades (normal, mild, moderate and severe hypernasality) based on vocal tract characteristics. Linear prediction (LP) analysis is widely used to model the vocal tract. Glottal source information may be included in the LP-based spectrum. The stabilized weighted linear prediction (SWLP) method, which imposes the temporal weights on the closed-phase interval of the glottal cycle, is a more robust approach for modeling the vocal tract. The extended weighted linear prediction (XLP) method weights each lagged speech signal separately, which achieves a finer time scale on the spectral envelope than the SWLP method. Tested speech recordings were collected from 60 subjects with cleft palate and 20 control subjects, and included a total of 4640 Mandarin syllables. The experimental results showed that the spectral envelope of normal speech decreases faster than that of hypernasal speech in the high-frequency part. The experimental results also indicate that the SWLP- and XLP-based methods have smaller correlation coefficients between normal and hypernasal speech than the LP method. Thus, the SWLP and XLP methods have better ability to distinguish hypernasal from normal speech than the LP method. The classification accuracies of the four hypernasality grades using the SWLP and XLP methods range from 83.86% to 97.47%. The selection of the model order and the size of the weight function are also discussed in this paper.

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

Assessment of intelligibility is required to characterize the overall speech production capability and to measure the speech outcome of different interventions for individuals with cleft lip and palate (CLP). Researchers have found that articulation error and hypernasality have a significant effect on the degradation of CLP speech intelligibility. Motivated by this finding, the present work proposes an objective measure of sentence-level intelligibility by combining the information of articulation deficits and hypernasality. These two speech disorders represent different aspects of CLP speech. Hence, it is expected that the composite measure based on them may utilize complementary clinical information. The objective scores of articulation and hypernasality are used as features to train a regression model, and the output of the model is considered as the predicted intelligibility score. The Spearman's correlation coefficient based analysis shows a significant correlation between the predicted and perceptual intelligibility scores (ρ = 0.77, p < 0.001).

Detection of Nasalized Voiced Stops in Cleft Palate Speech Using Epoch-Synchronous Features

The presence of velopharyngeal dysfunction in individuals with cleft palate CP nasalizes the voiced stops. Due to this, voiced stops /b/, /d/, /g/ tend to be perceive like nasal consonants /m/, /n/, /ng/. In this work, a novel algorithm is proposed for the detection of nasalized voiced stops in CP speech using epoch-synchronous features. Speech regions corresponding to consonant and consonant-vowel transitions are segmented using the knowledge of glottal activity, syllable nucleus, low-frequency spectral dominance, and vowel onset point. The segmented regions are epoch-synchronously processed to analyze the spectral, spectro-temporal, excitation source, and periodicity characteristics of normal and nasalized voiced stops. Spectral and spectro temporal features are computed using single pole filter based time-frequency representation. The amplitude of Hilbert envelope of linear prediction residual, measured around the epoch is used to analyze the effect of nasalization on excitation source. Comparison of speech frames of successive inter-epoch intervals is carried out to analyze the periodicity characteristics. The proposed features are used to develop a support vector machine classifier for the classification of normal and nasalized voiced stops. Segmentation accuracy for the proposed knowledge based method is found to be better than the hidden Markov model based force-alignment approach. The detection rate of nasalized voiced stops is found to be high for the proposed epoch synchronous features than the conventional Mel-frequency cepstral coefficients.

The Impact of Real-Time Articulatory Information on Phonetic Transcription: Ultrasound-Aided Transcription in Cleft Lip and Palate Speech

Objective: This study investigated whether adding an additional modality, namely ultrasound tongue imaging (UTI), to perception-based phonetic transcription impacted on the identification of compensatory articulations and on interrater reliability. Patients and Methods: Thirty-nine English-speaking children aged 3–12 years with cleft lip and palate (CLP) were recorded producing repetitions of /aCa/ for all places of articulation with simultaneous audio recording and probe-stabilized ultrasound (US). Three types of transcriptions were performed: (1) descriptive observations from the live US by the clinician recording the data, (2) US-aided transcription (UA) by two US-trained clinicians, and (3) traditional phonetic transcription by two CLP specialists from audio recording. We compared the number of consonants identified as in error by each transcriber and then classified errors into eight different subcategories. Results: Both UA and traditional transcription yielded similar error detection rates; however, these were significantly higher than the observations recorded live in the clinic. Interrater reliability for the US transcribers was substantial (κ = 0.65) compared to moderate (κ = 0.47) for the traditional transcribers. US transcribers were more likely to identify covert errors such as double articulations and retroflexion than the audio-only transcribers. Conclusion: UTI is a useful complement to traditional phonetic transcription for CLP speech.

HypernasalityNet: Deep recurrent neural network for automatic hypernasality detection

BackgroundCleft palate patients have inability to produce adequate velopharyngeal closure, which results in hypernasal speech. In clinic, hypernasal speech is assessed through subject assessment by speech language pathologists. Automatic hypernasal speech detection can provide aided diagnoses for speech language pathologists and clinicians. ObjectivesThis study aims to develop Long Short-Term Memory (LSTM) based Deep Recurrent Neural Network (DRNN) system to detect hypernasal speech from cleft palate patients, thus to provide aided diagnoses for clinical operation and speech therapy. Meanwhile, the feature mining and classification abilities of LSTM-DRNN system are explored. MethodsThe utilized speech recordings are 14,544 vowels in Mandarin. Speech data is collected from 144 children (72 children with hypernasality and 72 controls) with the age of 5–12 years old. This work proposes a LSTM based DRNN system to achieve automatic hypernasal speech detection, since LSTM-DRNN can learn short-time dependences of hypernasal speech. The vocal tract based features are fed into LSTM-DRNN to achieve deep mining of features. To verify the feature mining ability of LSTM-DRNN, features projected by LSTM-DRNN are fed into shallow classifiers instead of the following two fully connected layers and a softmax layer. And the features without the projecting process of LSTM-DRNN are directly fed into shallow classifiers as a comparison. Hypernasality-sensitive vowels (/a/, /i/, and /u/) are analyzed for the first time. ResultsThis LSTM-DRNN based hypernasal speech detection method reaches higher detection accuracy than that using shallow classifiers, since LSTM-DRNN mines features through time axis and network depth simultaneously. The proposed LSTM-DRNN based hypernasality detection system reaches the highest accuracy of 93.35%. According to the analysis of hypernasality-sensitive vowels, the experimental result concludes that vowels /i/ and /u/ are the most sensitive vowels to hypernasal speech. ConclusionsThe results show that LSTM-DRNN has robust feature mining ability and classification ability. This is the first work that applies the LSTM-DRNN technique to automatically detect hypernasality in cleft palate speech. The experimental results demonstrate the potential of deep learning on pathologist speech detection.

Automatic Hypernasality Detection in Cleft Palate Speech Using CNN

Automatic hypernasality detection in cleft palate speech can facilitate diagnosis by speech-language pathologists. This paper describes a feature-independent end-to-end algorithm that uses a convolutional neural network (CNN) to detect hypernasality in cleft palate speech. A speech spectrogram is adopted as the input. The average F1-scores for the hypernasality detection task are 0.9485 and 0.9746 using a dataset that is spoken by children and a dataset that is spoken by adults, respectively. The experiments explore the influence of the spectral resolution on the hypernasality detection performance in cleft palate speech. Higher spectral resolution can highlight the vocal tract parameters of hypernasality, such as formants and spectral zeros. The CNN learns efficient features via a two-dimensional filtering operation, while the feature extraction performance of shallow classifiers is limited. Compared with deep neural network and shallow classifiers, CNN realizes the highest F1-score of 0.9485. Comparing various network architectures, the convolutional filter of size 1 × 8 achieves the highest F1-score in the hypernasality detection task. The selected filter size of 1 × 8 considers more frequency information and is more suitable for hypernasality detection than the filters of size 3 × 3, 4 × 4, 5 × 5, and 6 × 6. According to an analysis of hypernasality-sensitive vowels, the experimental result concludes that the vowel /i/ is the most sensitive vowel to hypernasality. Compared with state-of-the-art literature, the proposed CNN-based system realizes a better detection performance. The results of an experiment that is conducted on a heterogeneous corpus demonstrate that CNN can better handle the speech variability compared with the shallow classifiers.

Tongue-palate contact for nasal versus oral stops in speakers with repaired cleft palate

ABSTRACTMost previous studies of speech disorders associated with cleft palate have reported a higher incidence of errors for oral stops, fricatives and affricates compared to nasal stops. However, the results of a recent ultrasound study have raised the possibility that errors affecting nasal consonants might not be as rare as originally thought. A review of the electropalatography (EPG) literature on cleft palate speech has also shown that atypical tongue-palate contact patterns can occur during nasal consonants and that nasal and oral stops are often produced with similar atypical lingual gestures. Therefore, this study investigated the production of nasal stops (/n/and/ŋ/) and the homorganic oral stops (/t/,/d/and/k/,/ɡ/respectively) in eight children with repaired cleft palate using perceptual judgements and evaluation of tongue-palate contact patterns. Results of the perceptual judgements support the findings in the literature that there was a higher per cent phoneme correct for the alveolar nasal (about 90%) than for the oral stops (60–70%). However, there was a low per cent phoneme correct for the velar nasal (about 50%) and the per cent correct as determined by the EPG data was lower than those based on perceptual judgements. Two children showed similar atypical articulatory gestures for the oral and nasal alveolar stops. We discuss the possibility that the nasal errors may be of phonemic as opposed to phonetic origin. The results underscore the importance of considering the phonological dimension of production when assessing the speech of children in this clinical group.

Treating Children With Cleft Palate: Case Examples

Purpose Treatment of a child with cleft palate is often complex and requires collaboration between treating speech-language pathologists (SLPs) and members of the cleft palate team. This article uses a case study format to facilitate discussion between 2 SLPs with specialty training in cleft palate speech disorders. The purpose of this article is to use a case study and response approach to facilitate a conversation that explores challenges faced and differing treatment approaches to reach the same goal of typical speech development for a child with cleft palate. Conclusion The discussion between the treating SLP and the responding SLP provides examples of meeting comparable goals in different ways, highlighting similarities and differences in treatment approaches, while encouraging continued conversations and community among cleft palate speech specialists.

Effect of Prompts for Restructuring Oral Muscular Phonetic Targets (PROMPT) on Compensatory Articulation in Children With Cleft Palate/Lip.

Objective. This investigation researched the effectiveness of the PROMPT (Prompts for Restructuring Oral Muscular Phonetic Targets) method to address compensatory articulation errors in children with cleft palate. Design. Single-subject AB multiple baselines across participants and behaviors. Setting. Pediatric outpatient rehabilitation department in a local hospital in a metropolitan city. Participants. The investigation consisted of 3 participants (ages = 4:4 to 12:8) born with bilateral complete cleft lip and palate. All participants underwent several reconstructive surgeries to repair their lips and palates. Interventions. The PROMPT treatment was provided for 45 minutes 3 times a week for 4 weeks (3 weeks for Participant 2). Main Outcome Measure. Therapy sessions addressed anterior lingual speech motor phonemes across 3 tiers (syllables, words, and phrases). Results. Direct visual observation of data obtained throughout this investigation indicate potential positive effects and significant correlation between improvements in sound production at 3 tiers and the implementation of the PROMPT technique. Speech intelligibility was judged by 3 blinded listeners who were unfamiliar with children with speech disorders or with cleft palate speech. All listeners identified and judged improvement in overall speech intelligibility over the course of this investigation. Listeners examined speech samples selected from sessions 3, 6, 9, and 12. Conclusion. The findings in this investigation provide a potential relationship on the effectiveness of the PROMPT method and attainment of accurate speech productions in children with cleft palate producing compensatory articulation errors, resulting in improvement in overall speech intelligibility.

Automatic detection of consonant omission in cleft palate speech

Consonant omission is one of the most typical and common articulation disorders in cleft palate (CP) speech. The automatic evaluation of consonant omission provides an objective and aided diagnosis to speech-language pathologists and CP patients. This work proposes an automatic consonant omission method. The collection of pathologic speech data is far more difficult than that of normal speech. The speech samples applied in this work are collected from 80 CP patients, with annotation on the phonemic level by professional speech-language pathologists. The proposed method requires no pre-training or modeling, by taking advantages of priori knowledge of CP speech and Chinese phonetics. The classification between voiced initials and finals is a difficulty in Mandarin speech processing researches, this work proposes a time-domain waveform difference analysis method to address this difficulty. The proposed method achieves the accuracy of 88.9% for consonant omission detection in CP speech, and the sensitivity and specificity of the proposed method are 70.89% and 91.86% respectively.

Automatic Detection Algorithm of Pharyngeal Fricatives in Cleft Palate Speech Based on LPIF and Feature Selection

Cleft palate is one of common congenital malformations that has huge impacts on the physical and psychological health of patients. Pharyngeal fricative in cleft palate speech is a kind of common compensatory articulations, which is produced by retracting tongue position to posterior pharyngeal wall and narrowing velopharyngeal opening. In this paper, based on voice mechanism of pharyngeal fricatives in cleft palate speech, linear prediction inverse filter was used to extract glottal waveform and estimate vocal tract model coefficients. Then four features were extracted, including pitch period, glottal flow derivative waveform, vocal tract area and vocal tract gain. The cross-correlation function was used to calculate the correlation between features. Glottal flow derivative waveform was removed since it had strong correlation with the others. KNN classifier was applied to realize the automatic pharyngeal fricatives detection in cleft palate speech, which reaches the detection accuracy of 98.40%.

Importance of glottis landmarks for the assessment of cleft lip and palate speech intelligibility.

The present work explores the acoustic characteristics of articulatory deviations near g(lottis) landmarks to derive the correlates of cleft lip and palate speech intelligibility. The speech region around the g landmark is used to compute two different acoustic features, namely, two-dimensional discrete cosine transform based joint spectro-temporal features, and Mel-frequency cepstral coefficients. Sentence-specific acoustic models are built using these features extracted from the normal speakers' group. The mean log-likelihood score for each test utterance is computed and tested as the acoustic correlates of intelligibility. Derived intelligibility measure shows significant correlation (ρ = 0.78, p < 0.001) with the perceptual ratings.

Intelligibility assessment of cleft lip and palate speech using Gaussian posteriograms based on joint spectro-temporal features.

Intelligibility is considered as one of the primary measures for speech rehabilitation of individuals with a cleft lip and palate (CLP). Currently, speech processing and machine-learning-based objective methods are gaining more research interest as a way to quantify speech intelligibility. In this work, joint spectro-temporal features computed from a time-frequency representation of speech are explored to derive speech representations based on Gaussian posteriograms. A comparative framework using dynamic time warping (DTW) is used to quantify the intelligibility of child CLP speech. The DTW distance is used to score sentence-level intelligibility and tested for correlation with perceptual intelligibility ratings obtained from expert speech-language pathologists. A baseline DTW system using the conventional Mel-frequency cepstral coefficients (MFCCs) is also developed to compare the performance of the proposed system. Spearman's rank correlation coefficient between the objective intelligibility scores and the perceptual intelligibility rating is studied. A Williams significance test is conducted to assess the statistical significance of the correlation difference between the methods. The results show that the system based on joint spectro-temporal features significantly outperforms the MFCC-based system.

Quality of Speech Following Cleft Palate Surgery in Children

Background: Surgical treatment of cleft palate is accompanied with speech problems. Speech therapy in these children after surgery can improve their speech. In this study, we aimed to evaluate the quality of speaking in operated cleft palate patients and speech therapy effects in a small group of these patients. Methods: In this cross-sectional study, speech quality of 55 children with operated cleft palate was assessed regarding resonance, audible nasal emission, consonant production and speech acceptability. Speech outcomes after therapy were evaluated in 19 patients. Results: Cleft palate types were unilateral cleft and lip palate in 18 cases, bilateral cleft and lip palate in 4 cases, secondary cleft palate type in 30 cases and of mere-soft palate in 3 cases. Thirty-five children were operated during the first year of life and 20 were operated after the first year. More than 55% of patients had normal hypernasality with few cases of severe hypernasality and less than 45% had error in consonant production. Patients operated during first year of life had more speech problems. Speech parameters were improved in 19 patients after speech therapy. Conclusion: In conclusion, children with cleft palate have some degrees of speech disorders after repair surgery than could be improved by the speech therapy. Speech therapy should be considered as one of the main treatment protocols along with repair surgery in children with cleft palate.

Automatic detection of pharyngeal fricative in cleft palate speech

Pharyngeal fricative occurs during the production of consonants, which makes the consonants lose or weaken in cleft palate speech. In clinical application, the automatic detection of pharyngeal fricative in cleft palate speech could provide objective and effective assistant aids for speech language pathologists. In this paper, a novel acoustic parameter is proposed to detect the existence of pharyngeal fricative in cleft palate speech. This proposed acoustic feature ICPD (Independent Consonant Prominent Distribution) reflects the movement of mouth and tongue. The experimental results show that normal fricative has the higher ICPD. The extracted ICPD feature is combined with k-nearest neighbor classifier to achieve the automatic detection of pharyngeal fricative. The proposed system is tested on 127 speech samples recorded by cleft palate patients and 94 by normal speakers of controls. The overall pharyngeal fricative detection accuracy is around 90%.

Australian children with cleft palate achieve age-appropriate speech by 5 years of age

IntroductionChildren with cleft palate demonstrate atypical speech sound development, which can influence their intelligibility, literacy and learning. There is limited documentation regarding how speech sound errors change over time in cleft palate speech and the effect that these errors have upon mono-versus polysyllabic word production. The objective of this study was to examine the phonetic and phonological speech skills of children with cleft palate at ages 3 and 5. MethodsA cross-sectional observational design was used. Eligible participants were aged 3 or 5 years with a repaired cleft palate. The Diagnostic Evaluation of Articulation and Phonology (DEAP) Articulation subtest and a non-standardised list of mono- and polysyllabic words were administered once for each child. The Profile of Phonology (PROPH) was used to analyse each child's speech. ResultsN = 51 children with cleft palate participated in the study. Three-year-old children with cleft palate produced significantly more speech errors than their typically-developing peers, but no difference was apparent at 5 years. The 5-year-olds demonstrated greater phonetic and phonological accuracy than the 3-year-old children. Polysyllabic words were more affected by errors than monosyllables in the 3-year-old group only. ConclusionsChildren with cleft palate are prone to phonetic and phonological speech errors in their preschool years. Most of these speech errors approximate typically-developing children by 5 years. At 3 years, word shape has an influence upon phonological speech accuracy. Speech pathology intervention is indicated to support the intelligibility of these children from their earliest stages of development.

Automatic initial and final segmentation in cleft palate speech of Mandarin speakers.

The speech unit segmentation is an important pre-processing step in the analysis of cleft palate speech. In Mandarin, one syllable is composed of two parts: initial and final. In cleft palate speech, the resonance disorders occur at the finals and the voiced initials, while the articulation disorders occur at the unvoiced initials. Thus, the initials and finals are the minimum speech units, which could reflect the characteristics of cleft palate speech disorders. In this work, an automatic initial/final segmentation method is proposed. It is an important preprocessing step in cleft palate speech signal processing. The tested cleft palate speech utterances are collected from the Cleft Palate Speech Treatment Center in the Hospital of Stomatology, Sichuan University, which has the largest cleft palate patients in China. The cleft palate speech data includes 824 speech segments, and the control samples contain 228 speech segments. The syllables are extracted from the speech utterances firstly. The proposed syllable extraction method avoids the training stage, and achieves a good performance for both voiced and unvoiced speech. Then, the syllables are classified into with “quasi-unvoiced” or with “quasi-voiced” initials. Respective initial/final segmentation methods are proposed to these two types of syllables. Moreover, a two-step segmentation method is proposed. The rough locations of syllable and initial/final boundaries are refined in the second segmentation step, in order to improve the robustness of segmentation accuracy. The experiments show that the initial/final segmentation accuracies for syllables with quasi-unvoiced initials are higher than quasi-voiced initials. For the cleft palate speech, the mean time error is 4.4ms for syllables with quasi-unvoiced initials, and 25.7ms for syllables with quasi-voiced initials, and the correct segmentation accuracy P30 for all the syllables is 91.69%. For the control samples, P30 for all the syllables is 91.24%.

Parent-led Articulation Therapy in Cleft Palate Speech: A Feasibility Study

Objective: To test the feasibility of trained parents undertaking cleftrelated articulation therapy, supervised by a Specialist Speech &amp; Language Therapist using Connected Health, with a view to a full trial. Method: There were five components: (1) to identify the number of 3âĂŠ4-year-olds who could potentially benefit from this programme, through reviewing the charts of children with cleft palate in one cleft centre; (2) to develop an appropriate speech assessment protocol identifying the primary and secondary outcome measures; (3) to evaluate Connected Health for interacting with children and parents; (4) to develop the parent-training course; and (5) to test the feasibility of the parent training and implementation of the intervention programme with four parent/child diads. Main results: Approximately 25% of 3-year-olds might be eligible. The assessment protocol was largely successful, with minor adaptations recommended. Audio/video quality, using FaceTime, was reported as good most of the time by parents and the SLT. The parents showed evidence of learning from the 2-day parent training course. Post-intervention assessments indicated that all four children showed progress. Conclusions: Results indicated that PLAT should be evaluated in a randomized controlled trial, with adaptations to the age range, inclusion/exclusion criteria and parental support.

Automatic detection of glottal stop in cleft palate speech

The speech therapy is essential during the whole treatment of Cleft Palate (CP) over many years. The automatic evaluation of CP speech could provide an effective assistant diagnosis. The glottal stop is a typical compensatory articulation error in CP speech. It is produced by adducting the vocal folds as a substitution during the pronunciation of oral pressure consonants. The existence of glottal stop has a great impact on speech intelligibility. In this work, an automatic glottal stop detection system is proposed. The CP speech database is collected by the Hospital of Stomatology, Sichuan University, which has the largest number of CP patients in China. This database includes extensive CP speech samples annotated by speech-language pathologists at the phoneme level. The vocabulary of this database includes all the initial consonants in Mandarin. The automatic initials and finals segmentation method is proposed firstly. Then, for the pressure initial consonants, four types of acoustic features are extracted: Mel-frequency cepstral coefficients, formants, Gammatone filtering energy feature, wavelet packet energy and Shannon entropy features. The features are processed using a k-nearest neighbor classifier. The k-fold cross validation is used to calculate the average detection accuracy, which reaches up to 93.5% using Gammatone filtering energy feature.

The analysis and detection of hypernasality based on a formant extraction algorithm

In the clinical practice, the effective assessment of cleft palate speech disorders is important. For hypernasal speech, the resonance between nasal cavity and oral cavity causes an additional nasal formant. Thus, the formant frequency is a crucial cue for the judgment of hypernasality in cleft palate speech. Due to the existence of nasal formant, the peak merger occurs to the spectrum of nasal speech more often. However, the peak merger could not be solved by classical linear prediction coefficient root extraction method. In this paper, a method is proposed to detect the additional nasal formant in low-frequency region and obtain the formant frequency. The experiment results show that the proposed method could locate the nasal formant preferably. Moreover, the formants are regarded as the extraction features to proceed the detection of hypernasality. 436 phonemes, which are collected from Hospital of Stomatology, are used to carry out the experiment. The detection accuracy of hypernasality in cleft palate speech is 95.2%.