No abstract

No abstract

ABSTRACT

No abstract

No abstract

BackgroundSpeech production and speech phonetic features gradually improve in children by obtaining audio feedback after cochlear implantation or using hearing aids. The aim of this study was to develop and evaluate automated classification of voice disorder in children with cochlear implantation and hearing aids.MethodsWe considered 4 disorder categories in children's voice using the following definitions:Level_1: Children who produce spontaneous phonation and use words spontaneously and imitatively.Level_2: Children, who produce spontaneous phonation, use words spontaneously and make short sentences imitatively.Level_3: Children, who produce spontaneous phonations, use words and arbitrary sentences spontaneously.Level_4: Normal children without any hearing loss background. Thirty Persian children participated in the study, including six children in each level from one to three and 12 children in level four. Voice samples of five isolated Persian words "mashin", "mar", "moosh", "gav" and "mouz" were analyzed. Four levels of the voice quality were considered, the higher the level the less significant the speech disorder. "Frame-based" and "word-based" features were extracted from voice signals. The frame-based features include intensity, fundamental frequency, formants, nasality and approximate entropy and word-based features include phase space features and wavelet coefficients. For frame-based features, hidden Markov models were used as classifiers and for word-based features, neural network was used.ResultsAfter Classifiers fusion with three methods: Majority Voting Rule, Linear Combination and Stacked fusion, the best classification rates were obtained using frame-based and word-based features with MVR rule (level 1:100%, level 2: 93.75%, level 3: 100%, level 4: 94%).ConclusionsResult of this study may help speech pathologists follow up voice disorder recovery in children with cochlear implantation or hearing aid who are in the same age range.

Chronic pain has been thought to induce muscular changes in chronic tension-type headache (CTTH) patients. As the knowledge of muscular responses in CTTH is inconsistent, we decided to introduce new electromyogram signal shape descriptors. We also wanted to compare the discriminatory power of proposed indices with classical measures to establish their potential to act as markers for CTTH. Thirty-eight headache patients with twenty healthy volunteers were recruited. Twenty patients had CTTH, while 18 had migraine without aura. Surface electromyogram data were recorded from right sternocleidomastoid and left temporalis muscles during rest and in a headache-free situation. Besides conventional root mean square (RMS) and median frequency (MDF), two morphological-based indices, skewness and kurtosis, were proposed to quantify the shape variations of signal distribution. Results demonstrated that the skewness outperformed RMS and MDF in terms of discriminatory power (p < 0.00). Kurtosis values for both muscles differed considerably among study groups (p < 0.04). RMS for both muscles was noticeably higher in CTTH group (p < 0.00). Regarding MDF, migraineurs revealed highest (p < 0.05), while CTTH patients represented the lowest values. Skewness was the most relevant predictor for headache diagnosis, especially in temporalis muscle (migraine, odds ratio = 21.1, p = 0.01; Ctension-type headache, odds ratio = 78.8, p = 0.00). There are detectable distinct muscular responses in chronic headache sufferers. This finding could be due to adaptation to muscle underuse or sustained contraction, leading to impaired recruitment and muscle fiber-type conversion with dominant type I fibers in CTTH.

No abstract