Objective evaluation of speech dysfluencies using wavelet packet transform with sample entropy

Dysfluency and stuttering are a break or interruption of normal speech such as repetition, prolongation, interjection of syllables, sounds, words or phrases and involuntary silent pauses or blocks in communication. Stuttering assessment through manual classification of speech dysfluencies is subjective, inconsistent, time consuming and prone to error. This paper proposes an objective evaluation of speech dysfluencies based on the wavelet packet transform with sample entropy features. Dysfluent speech signals are decomposed into six levels by using wavelet packet transform. Sample entropy (SampEn) features are extracted at every level of decomposition and they are used as features to characterize the speech dysfluencies (stuttered events). Three different classifiers such as k-nearest neighbor (kNN), linear discriminant analysis (LDA) based classifier and support vector machine (SVM) are used to investigate the performance of the sample entropy features for the classification of speech dysfluencies. 10-fold cross validation method is used for testing the reliability of the classifier results. The effect of different wavelet families on the classification performance is also performed. Experimental results demonstrate that the proposed features and classification algorithms give very promising classification accuracy of 96.67% with the standard deviation of 0.37 and also that the proposed method can be used to help speech language pathologist in classifying speech dysfluencies.     

Effect of intermediate layer on gas separation performance of disk supported carbon membrane

Porous alumina disk ceramic was decorated with various types of intermediate layers via one-step spray coating-carbonization technique. P-84 (BTDA-TDI/MDI) polymeric solution was sprayed on the alumina disk with an incorporation of intermediate layer. The membrane was carbonized at 700°C under nitrogen (N₂) atmosphere with a heating rate of 3°C/min. The resultant carbon membrane was characterized in terms of its thermal stability, structural morphology, and gas permeation properties. A high-performance carbon membrane was obtained with the intermediate layer of the alumina powder, which exhibited the best selectivity of O₂/N₂, CO₂/N₂ and CO₂/CH₄ of 4.39, 19.89 and 58.43, respectively.     

Electrocardiogram‐based emotion recognition system using empirical mode decomposition and discrete Fourier transform

Emotion recognition using physiological signals has gained momentum in the field of human computer–interaction. This work focuses on developing a user‐independent emotion recognition system that would classify five emotions (happiness, sadness, fear, surprise and disgust) and neutral state. The various stages such as design of emotion elicitation protocol, data acquisition, pre‐processing, feature extraction and classification are discussed. Emotional data were obtained from 30 undergraduate students by using emotional video clips. Power and entropy features were obtained in three ways – by decomposing and reconstructing the signal using empirical mode decomposition, by using a Hilbert–Huang transform and by applying a discrete Fourier transform to the intrinsic mode functions (IMFs). Statistical analysis using analysis of variance indicates significant differences among the six emotional states (p < 0.001). Classification results indicate that applying the discrete Fourier transform instead of the Hilbert transform to the IMFs provides comparatively better accuracy for all the six classes with an overall accuracy of 52%. Although the accuracy is less, it reveals the possibility of developing a system that could identify the six emotional states in a user‐independent manner using electrocardiogram signals. The accuracy of the system can be improved by investigating the power and entropy of the individual IMFs.     

Incorporation of thermally labile additives in polyimide carbon membrane for hydrogen separation

In this study, three thermally labile additives microcrystalline cellulose (MCC), nanocrystalline cellulose (NCC), and polyvinylpyrrolidone (PVP) were introduced to the P84-copolyimide (PI) solution. PI-based carbon tubular membranes were fabricated using dip-coating method, followed by sample characterizations in order to determine their structural morphologies, thermal stability and gas permeation performance. NCC was added as the membrane pore former for the hydrogen gas (H₂) separation. While tests involving pure H₂ and N₂ permeation were carried out at room temperature, carbon membranes were carbonized at a final temperature of 800 °C, with the heating rate of 3 °C/min under the Ar flow. Excellent result of H₂/N₂ selectivity was obtained with value of 430.06 ± 4.16. Addition of NCC has significantly increased the number of pore channels in the membrane, hence, contributing to high gas permeance and selectivity. NCC has shown potential as a good additive for an enhanced hydrogen separation performance.     

Carbon tubular membranes from nanocrystalline cellulose blended with P84 co-polyimide for H2 and He separation

In this study, carbon tubular membranes were produced by employing P84 co-polyimide as a precursor material and nanocrystalline cellulose (NCC) as an additive. The synthesized NCC which was derived from recycled newspaper was used as a pore forming agent for the membrane. Various carbonization temperatures (600, 700, 800, and 900 °C) were used while the stabilization temperature was kept at 300 °C. The measurements of pure gases' (He, H₂, and N₂) permeance through all carbon tubular membranes produced were carried out at feed pressure of 8 bars. The results showed that higher carbonization temperatures resulted in more selective but less productive carbon membranes. The outcome of this study suggested that carbon tubular membrane fabricated from NCC blending with P84 co-polyimide as a promising candidate for H₂ and He recovery application with H₂/N₂ and He/N₂ selectivity of 434.68 ± 1.39 and 463.86 ± 8.12, respectively.     

Classification of speech dysfluencies with MFCC and LPCC features

The goal of this paper is to discuss comparison of speech parameterization methods: Mel-Frequency Cepstrum Coefficients (MFCC) and Linear Prediction Cepstrum Coefficients (LPCC) for recognizing the stuttered events. Speech samples from UCLASS are used for our analysis. The stuttered events are identified through manual segmentation and used for feature extraction. Two simple classifiers are used for testing the proposed features. Conventional validation method is used for testing the reliability of the classifier. The experimental investigation elucidates MFCC and LPCC features which can be used for identifying the stuttered events and LPCC features were slightly outperformed than MFCC features.     

Matrimid‐based carbon tubular membranes: The effect of the polymer composition

In this article, we present a development study of new membrane materials and enhancements of productive membranes to improve the current performance of polymeric membranes. Carbon membranes are a promising material for this matter as they offer an improvement in the gas‐separation performance and exhibit a good combination of permeability and selectivity. Carbon membranes produced from the carbonization of polymeric materials have been reported to be effective for gas separation because of their ability to separate gases with almost similar molecular sizes. In this study, a carbon support membrane was prepared with Matrimid 5218 as a polymeric precursor. The polymer solution was coated on the surface of a tubular support with the dip‐coating method. The polymer tubular membrane was then carbonized under a nitrogen atmosphere with different polymer compositions of 5–18 wt %. The carbonization process was performed at 850°C at a heating rate of 2°C/min. Matrimid‐based carbon tubular membranes were fabricated and characterized in terms of their structural morphology, thermal stability, and gas‐permeation properties with scanning electron microscopy, thermogravimetric analysis, Fourier transform infrared spectroscopy, and a pure‐gas‐permeation system, respectively. Pure‐gas‐permeation tests were performed with the pure gases carbon dioxide (CO₂) and N₂ at room temperature at a pressure of 8 bar. On the basis of the results, the highest CO₂/N₂ selectivity of 75.73 was obtained for the carbon membrane prepared with a 15 wt % polymer composition. © 2015 Wiley Periodicals, Inc. J. Appl. Polym. Sci. 2015 , 132, 42394.     

A comparative study of wavelet families for classification of wrist motions

The selection of most suitable mother wavelet function is still an open research problem in various signal and image processing applications. This paper presents a comparative study of different wavelet families (Daubechies, Symlets, Coiflets, and Biorthogonal) for analysis of wrist motions from electromyography (EMG) signals. EMG signals are decomposed into three levels using discrete wavelet packet transform. From the decomposed EMG signals, root mean square (RMS) value, autoregressive (AR) model coefficients (4th order) and waveform length (WL) are extracted. Two data projection methods such as principal component analysis (PCA) and linear disciminant analysis (LDA) are used to reduce the dimensionality of the extracted features. Probabilistic neural network (PNN) and general regression neural network (GRNN) are employed to classify the different types of wrist motions, which gives a promising accuracy of above 99%. From the analysis, we inferred that ‘Biorthogonal’ and ‘Coiflets’ wavelet families are more suitable for accurate classification of EMG signals of different wrist motions.     

Normal and hypoacoustic infant cry signal classification using time-frequency analysis and general regression neural network

Crying is the most noticeable behavior of infancy. Infant cry signals can be used to identify physical or psychological status of an infant. Recently, acoustic analysis of infant cry signal has shown promising results and it has been proven to be an excellent tool to investigate the pathological status of an infant. This paper proposes short-time Fourier transform (STFT) based time-frequency analysis of infant cry signals. Few statistical features are derived from the time-frequency plot of infant cry signals and used as features to quantify infant cry signals. General Regression Neural Network (GRNN) is employed as a classifier for discriminating infant cry signals. Two classes of infant cry signals are considered such as normal cry signals and pathological cry signals from deaf infants. To prove the reliability of the proposed features, two neural network models such as Multilayer Perceptron (MLP) and Time-Delay Neural Network (TDNN) trained by scaled conjugate gradient algorithm are also used as classifiers. The experimental results show that the GRNN classifier gives very promising classification accuracy compared to MLP and TDNN and the proposed method can effectively classify normal and pathological infant cries.     

A hybrid expert system approach for telemonitoring of vocal fold pathology

Acoustical parameters extracted from the recorded voice samples are actively pursued for accurate detection of vocal fold pathology. Most of the system for detection of vocal fold pathology uses high quality voice samples. This paper proposes a hybrid expert system approach to detect vocal fold pathology using the compressed/low quality voice samples which includes feature extraction using wavelet packet transform, clustering based feature weighting and classification. In order to improve the robustness and discrimination ability of the wavelet packet transform based features (raw features), we propose clustering based feature weighting methods including k-means clustering (KMC), fuzzy c-means (FCM) clustering and subtractive clustering (SBC). We have investigated the effectiveness of raw and weighted features (obtained after applying feature weighting methods) using four different classifiers: Least Square Support Vector Machine (LS-SVM) with radial basis kernel, k-means nearest neighbor (kNN) classifier, probabilistic neural network (PNN) and classification and regression tree (CART). The proposed hybrid expert system approach gives a promising classification accuracy of 100% using the feature weighting methods and also it has potential application in remote detection of vocal fold pathology.