Intelligent stuttering speech recognition: A succinct review

Stuttering speech recognition is a well-studied concept in speech signal processing. Classification of speech disorder is the main focus of this study. Classification of stuttered speech is becoming more important with the enhancement of machine learning and deep learning. In this study, some of the recent and most influencing stuttering speech recognition methods are reviewed with a discussion on different categories of stuttering. The stuttering speech recognition process is divided mainly into four segments-input speech pre-emphasis, segmentation, feature extraction, and stutter classification. All these segments are briefly elaborated and related researches are discussed. It is observed that different traditional machine learning and deep learning classification approaches are employed to recognize stuttered speech in last few decades. A comprehensive analysis is presented on different feature extraction and classification method with their efficiency.

     

Effect of electron‐beam irradiation on ethylene–methyl acrylate copolymer

Ethylene–methyl acrylate copolymer (Elvaloy 1330) was irradiated by an electron beam at different levels of radiation both in the presence and absence of a trimethylolpropane trimethacrylate sensitizer at various dosages of incorporation. The mechanical, thermal, and electrical properties of these samples were compared. The mechanical properties were observed to reach an optimum maximum around 6 Mrad of irradiation and 1 phr of sensitizer incorporation. Furthermore, an increase in either the radiation dose or the sensitizer level helped very little to further modify the properties. The thermal properties as determined by the thermogravimetric analysis and differential scanning calorimetry studies were quite supportive of the observation made during the study of the mechanical properties. The thermal stability of the irradiated samples underwent an increase with increasing electron‐beam dosage. In a manner similar to those of the mechanical properties, the increase in thermal stability was found to reach a maximum at a particular level of treatment and sensitizer incorporation, beyond which there was marginal or no effect at all. The α transition temperature underwent a substantial increase with increasing crosslink density, as evidenced by the increase in gel content with increasing proportion of electron‐beam radiation dose. The other glass‐transition temperature, however, appeared to remain unaffected. The electrical properties, as described by the dielectric constant, volume resistivity, and breakdown voltage, appeared to be affected very little by the electron‐beam radiation. © 2008 Wiley Periodicals, Inc. J Appl Polym Sci, 2009     

Engineering properties of electron beam‐crosslinked ethylene methyl acrylate copolymer

Effect of electron beam on mechanical, thermal, and morphological properties of ethylene methyl acrylate copolymer, grade Elvaloy 1335 has been investigated. The copolymer was subjected to varying doses of electron beam radiation with different proportion of the sensitizer trimethylolpropane trimethacrylate (TMPTMA). It was observed that with increase in electron beam dose, the physicomechanical properties of the crosslinked copolymer improve, reaches an optimum level and subsequently deteriorates. The thermal properties as envisaged from thermogravimetric analysis and differential scanning calorimetric studies revealed stability of the crosslinked irradiated samples over that of the unirradiated ones. The thermal stability was also found to attain the maximum at the same level of radiation and sensitizer. The morphological studies showed consistency with the mechanical properties. Based on the overall study, it may be concluded that ethylene methyl acrylate copolymer with 1 phr TMPTMA at 60 kGy radiation dose is the optimum condition within the range studied in this investigation. © 2010 Wiley Periodicals, Inc. J Appl Polym Sci, 2010