Improving Deep Learning based Automatic Speech Recognition for Gujarati

We present a novel approach for improving the performance of an End-to-End speech recognition system for the Gujarati language. We follow a deep learning-based approach that includes Convolutional Neural Network, Bi-directional Long Short Term Memory layers, Dense layers, and Connectionist Temporal Classification as a loss function. To improve the performance of the system with the limited size of the dataset, we present a combined language model (Word-level language Model and Character-level language model)-based prefix decoding technique and Bidirectional Encoder Representations from Transformers-based post-processing technique. To gain key insights from our Automatic Speech Recognition (ASR) system, we used the inferences from the system and proposed different analysis methods. These insights help us in understanding and improving the ASR system as well as provide intuition into the language used for the ASR system. We have trained the model on the Microsoft Speech Corpus, and we observe a 5.87% decrease in Word Error Rate (WER) with respect to base-model WER.

Evaluation of optical properties of fluorescent nanofiber using image-processing technique

Purpose The purpose of this study is evaluate the optical properties of polyacrylonitrile (PAN) nanofibers containing fluorescent agents such as fluorescent dye and carbon quantum dots (CQDs) by using image-processing technique of Fluorescence microscope image. Design/methodology/approach The fluorescence microscope image of the pure PAN, PAN/CQDs and PAN/fluorescent dye nanofibers composite was analyzed using several image-processing techniques such as color histogram, lookup table (LUT), Fourier transform, RGB profile and surface plot analysis. Findings The fluorescence microscope image indicates that the fluorescence emission of nanocomposites depends on the type of fluorescent agent. The fluorescence intensity of nanofiber containing CQDs is more than nanofiber containing fluorescent dye. Various image-processing methods provide similar results for optical property of nanocomposites. Analyzing the LUT, the blue value of CQDs/PAN nanocomposite image was significantly higher than other nanocomposites. This was confirmed by other methods such as Fourier transform, color histogram and 3D topography of the electrospun nanofibers. According to analysis of colorimetric parameters, higher negative value of b* indicates bluer color for CQDs/PAN nanofibers than other nanocomposites. The obtained results indicate that the image-processing technique can be used to evaluate the optical property of fluorescent nanocomposite. Originality/value This study evaluates the optical properties of fluorescent nanocomposites by using image-processing techniques such as Fourier transform, color histogram, RGB profiles, LUT, surface plot and histogram analysis.

Dispersive MUSIC algorithm for Lamb wave phased array

By controlling the excitation time delay on each element, the conventional phased array can physically focus signals transmitted by different elements on a desired point in turn. An alternative and time-saving strategy is that every element takes turns to transmit the excitation and the remaining elements receive the corresponding response signals, which is known as the full matrix capture (FMC) method for data acquisition, and then let the signals virtually focus on every desired point by post-processing technique. In this study, based on the FMC, a dispersive multiple signal classification (MUSIC) algorithm for Lamb wave phased array is developed to locate defects. The virtual time reversal is implemented to back propagate the wave packets corresponding to the desired focusing point and a window function is adopted to adaptively isolate the desired packets from the other components. Then those wave packets are forward propagated to the original focusing point at a constant velocity. For every potential focusing point and all receivers, the virtual array focuses the signals from all transmitters so as to obtain the focusing signals. The MUSIC algorithm with the obtained focusing signals is adopted to achieve Lamb wave imaging. Benefiting from the post-processing operations, the baseline subtraction as well as the estimation for the number of the scattering sources is no longer required in the proposed algorithm. Experiments on an aluminum plate with three artificial defects and a compact circular PZT array are implemented and the results demonstrate the efficacy of the proposed algorithm.

Application of High-Intensity Ultrasound to Improve Food Processing Efficiency: A Review

The use of non-thermal processing technologies has grown in response to an ever-increasing demand for high-quality, convenient meals with natural taste and flavour that are free of chemical additions and preservatives. Food processing plays a crucial role in addressing food security issues by reducing loss and controlling spoilage. Among the several non-thermal processing methods, ultrasound technology has shown to be very beneficial. Ultrasound processing, whether used alone or in combination with other methods, improves food quality significantly and is thus considered beneficial. Cutting, freezing, drying, homogenization, foaming and defoaming, filtration, emulsification, and extraction are just a few of the applications for ultrasound in the food business. Ultrasounds can be used to destroy germs and inactivate enzymes without affecting the quality of the food. As a result, ultrasonography is being hailed as a game-changing processing technique for reducing organoleptic and nutritional waste. This review intends to investigate the underlying principles of ultrasonic generation and to improve understanding of their applications in food processing to make ultrasonic generation a safe, viable, and innovative food processing technology, as well as investigate the technology’s benefits and downsides. The breadth of ultrasound’s application in the industry has also been examined. This will also help researchers and the food sector develop more efficient strategies for frequency-controlled power ultrasound in food processing applications.

Voice adaptation by color-encoded frame matching as a multi-objective optimization problem for future games

Voice adaptation is an interactive speech processing technique that allows the speaker to transmit with a chosen target voice. We propose a novel method that is intended for dynamic scenarios, such as online video games, where the source speaker’s and target speaker’s data are nonaligned. This would yield massive improvements to immersion and experience by fully becoming a character, and address privacy concerns to protect against harassment by disguising the voice. With unaligned data, traditional methods, e.g., probabilistic models become inaccurate, while recent methods such as deep neural networks (DNN) require too substantial preparation work. Common methods require multiple subjects to be trained in parallel, which constraints practicality in productive environments. Our proposal trains a subject nonparallel into a voice profile used against any unknown source speaker. Prosodic data such as pitch, power and temporal structure are encoded into RGBA-colored frames used in a multi-objective optimization problem to adjust interrelated features based on color likeness. Finally, frames are smoothed and adjusted before output. The method was evaluated using Mean Opinion Score, ABX, MUSHRA, Single Ease Questions and performance benchmarks using two voice profiles of varying sizes and lastly discussion regarding game implementation. Results show improved adaptation quality, especially in a larger voice profile, and audience is positive about using such technology in future games.

Evaluation of the Effects of Processing Technique on Chemical Components in Raphani Semen by HPLC and UPLC-Q-TOF-MS

In this study, the effects of different processing techniques on the chemical components of Raphani Semen (RS) were evaluated. An established high-performance liquid chromatography (HPLC) method was adopted for the simultaneous determination of glucoraphanin, sinapine thiocyanate, raphanin, and erucic acid in the fried products of Raphani Semen to evaluate the chemical changes during frying processing as well as optimize the best frying technology of Raphani Semen. Then, the chemical components in the fried Raphani Semen were identified by ultrahigh-performance liquid chromatography-quadrupole time-of-flight mass spectrometry (UPLC-Q-TOF-MS). A total of 54 compounds in processed Raphani Semen were identified by UPLC-Q-TOF-MS. The results showed that the content of glucoraphanin and sinapine thiocyanate was the highest in the fried products at 130°C for 10 min, and the effect of “Enzyme Killing and Glycosides Preserving” was the best. Therefore, this condition was chosen as the best frying technology of Raphani Semen. This study provided a more scientific basis for evaluation of the quality of Raphani Semen fried products and optimization of the frying technology of Raphani Semen.

Pengaruh Komitmen Organisasi dan Organizational Citizenship Behavior Terhadap Kinerja Karyawan KOPTI Kabupaten Kuningan

Penelitian ini bertujuan untuk mengetahui: (1) Pengaruh komitmen organisasi terhadap kinerja karyawan koperasi produsen tempe tahu indonesia (KOPTI) Kabupaten Kuningan (2) Pengaruh organizational citizenship behavior terhadap kinerja karyawan koperasi produsen tempe tahu Indonesia (KOPTI) Kabupaten Kuningan (3) Pengaruh komitmen organisasi dan organizational citizenship behavior terhadap kinerja karyawan koperasi produsen tempe tahu indonesia (KOPTI) Kabupaten Kuningan. Jenis penelitian ini menggunakan metode deskriptif dan verifikatif dengan pendekatan kuantitatif. Populasi dalam penelitian ini adalah seluruh karyawan yang ada di Koperasi Produsen Tempe Tahu Indonesia (KOPTI) Kabupaten Kuningan sebanyak 37 orang, dengan Teknik pengambilan sampel menggunakan teknik sampling jenuh. Data yang digunakan adalah data primer dan sekunder. Hasil dari penelitian ini menunjukkan bahwa: (1) Komitmen organisasi berpengaruh positif dan signifikan terhadap kinerja karyawan. (2) organizational citizenship behavior berpengaruh positif dan signifikan terhadap kinerja karyawan. The purpose of this study was to determine the effect of organizational commitment and organizational citizenship behavior on employee performance. The method used is descriptive method with a quantitative approach. The population in this study were 37 employees of the Indonesian Kuningan Tofu and Tempe cooperative. The sampling technique was saturated sampling so that the samples obtained were all 37 employees of the Indonesian Tofu and Tempe Cooperative. The data processing technique used is multiple linear regression and hypothesis testing. The results of this study are organizational commitment and organizational citizenship behavior have a positive and significant effect on employee performance.

EFEKTIFITAS LATIHAN ABDOMINAL STRETCHING TERHADAP INTENSITAS NYERI HAID (DISMENOREA) PADA REMAJA PUTRI

Menstrual pain (dysmenorrhea) is one of the menstrual disorders that most women experience in adolescents. With one of the nonpharmacological practice stretching techniques can be done with the goal of knowing if there is an application effect on the intensity of menstrual pain (dysmenorrhea) in adolescents women. The type of research is an experimental design with the design approach used is the pre test- post test control group design, which is done in SMKN 01 makassar 2020 with 32 people research respondents, according to the two-split criteria for interagency and control groups as the pre-and post data processing technique on each group. Based on data normality tests, non-distribution of normal results, the tests used were wilcoxon tests. Furthermore, the pre-post normality test of unregulated data control interventions using the mann-whitney test.Research shows that test results on the pre post interventions using wilcoxon tests came p value (0,000 < 0.05). control groups using mann-whitney tests got p value (0,000<0.05). Thus it may be determined that there is an intermediate effect on the intensity of menstrual pain (dysmenorrhea).Based on the results of this study is expected for all elements that include educational agencies, subsequent researchers, teenagers and communities are able to provide information about abdominal tracks exercises as non-pharmacological therapy to reduce the intensity of hairsty pain (dysmenornea).