scholarly journals The Multi-Domain International Search on Speech 2020 ALBAYZIN Evaluation: Overview, Systems, Results, Discussion and Post-Evaluation Analyses

2021 ◽  
Vol 11 (18) ◽  
pp. 8519
Author(s):  
Javier Tejedor ◽  
Doroteo T. Toledano ◽  
Jose M. Ramirez ◽  
Ana R. Montalvo ◽  
Juan Ignacio Alvarez-Trejos
Keyword(s):  
Data Augmentation ◽  
Search Query ◽  
Spoken Term Detection ◽  
Post Evaluation ◽  
Highly Sensitive ◽  
Speech Data ◽  
Evaluation Metric ◽  
End Times ◽  
The Given ◽  
Search On Speech

The large amount of information stored in audio and video repositories makes search on speech (SoS) a challenging area that is continuously receiving much interest. Within SoS, spoken term detection (STD) aims to retrieve speech data given a text-based representation of a search query (which can include one or more words). On the other hand, query-by-example spoken term detection (QbE STD) aims to retrieve speech data given an acoustic representation of a search query. This is the first paper that presents an internationally open multi-domain evaluation for SoS in Spanish that includes both STD and QbE STD tasks. The evaluation was carefully designed so that several post-evaluation analyses of the main results could be carried out. The evaluation tasks aim to retrieve the speech files that contain the queries, providing their start and end times and a score that reflects how likely the detection within the given time intervals and speech file is. Three different speech databases in Spanish that comprise different domains were employed in the evaluation: the MAVIR database, which comprises a set of talks from workshops; the RTVE database, which includes broadcast news programs; and the SPARL20 database, which contains Spanish parliament sessions. We present the evaluation itself, the three databases, the evaluation metric, the systems submitted to the evaluation, the evaluation results and some detailed post-evaluation analyses based on specific query properties (in-vocabulary/out-of-vocabulary queries, single-word/multi-word queries and native/foreign queries). The most novel features of the submitted systems are a data augmentation technique for the STD task and an end-to-end system for the QbE STD task. The obtained results suggest that there is clearly room for improvement in the SoS task and that performance is highly sensitive to changes in the data domain.

Development and Validation of UV Spectroscopy Method for the Estimation of Dolutegravir in Bulk and Pharmaceutical Dosage Form

2021 ◽  
pp. 188-190
Author(s):  
Vaishnavi Dulange ◽  
G.B. Gajeli
Keyword(s):  
Dosage Form ◽  
Uv Spectroscopy ◽  
Spectroscopic Method ◽  
Water Mixture ◽  
Uv Spectrum ◽  
Pharmaceutical Dosage Form ◽  
Highly Sensitive ◽  
Development And Validation ◽  
The Given ◽  
Regression Correlation

UV spectroscopic method was developed for the estimation of Dolutegravir in bulk and Formulation.The UV spectrum of Dolutegravir in methanol and water mixture showed λ max at 254nm. Beer’s law is valid in the concentration range of 10-50µg/ml. This method was validated for linearity, accuracy, precision, LOD and LOQ. The method has demonstrated excellent linearity over the range of 10-50µg/ml with regression equation y = 0.030x + 0.008 and regression correlation coefficient r2= 0.998. Moreover, the method was found to be highly sensitive with LOD (2.056μg/ml) and LOQ (6.230μg/ml). Depending on results the given method can be successfully applied for assay of Dolutegravir in formulation.

Story Summarization Using a Question-Answering Approach

2021 ◽  
pp. 46-69
Author(s):  
Sanah Nashir Sayyed ◽  
Namrata Mahender C.
Keyword(s):  
Statistical Methods ◽  
Question Answering ◽  
Text Summarization ◽  
Loss Of Information ◽  
Representative Data ◽  
Minimal Loss ◽  
Speech Data ◽  
Linguistic Methods ◽  
The Given ◽  
Text Images

Summarization is the process of selecting representative data to produce a reduced version of the given data with a minimal loss of information; so, it generally works on text, images, videos, and speech data. The chapter deals with not only concepts of text summarization (types, stages, issues, and criteria) but also with applications. The two main categories of approaches generally used in text summaries (i.e., abstractive and extractive) are discussed. Abstractive techniques use linguistic methods to interpret the text; they produce understandable and semantically equivalent sentences with a shorter length. Extractive techniques mostly rely on statistical methods for extracting essential sentences from the given text. In addition, the authors explore the SACAS model to exemplify the process of summarization. The SACAS system analyzed 50 stories, and its evaluation is presented in terms of a new measurement based on question-answering MOS, which is also introduced in this chapter.

UV Spectrophotometric Method Development and Validation of Lignocaine Hydrochloride in Bulk and Semisolid Dosage Form

2021 ◽  
pp. 5280-5282
Author(s):  
Suyash Ingle ◽  
Varsha Tegeli ◽  
Avinash Birajdar ◽  
Vinod Matole ◽  
Sagar Adlinge ◽  
...  
Keyword(s):  
Spectrophotometric Method ◽  
Dosage Form ◽  
Method Development ◽  
Spectroscopic Method ◽  
Uv Spectrum ◽  
Highly Sensitive ◽  
Method Development And Validation ◽  
Development And Validation ◽  
The Given ◽  
Regression Correlation

Objective: A new, simple, sensitive, precise and reproducible UV spectroscopic method was developed for the estimation of Lignocaine Hydrochloride in bulk and Semisolid Formulation. Methods: The UV spectrum of Lignocaine Hydrochloride in RO water showed λ max at 228.8nm. Beer’s law is valid in the concentration range of 20-100µg/ml. This method was validated for linearity, accuracy, precision, ruggedness and robustness. Results: The method has demonstrated excellent linearity over the range of 20-100µg/ml with regression equation y = 0.0097x + 0.023 and regression correlation coefficient r2= 0.9992. Moreover, the method was found to be highly sensitive with LOD (3.55μg/ml) and LOQ (10.75μg/ml). Conclusion: Depending on results the given method can be successfully applied for assay of Lignocaine Hydrochloride in Semisolid formulation.

THE RESULTS OF EXPERIMENTAL STUDIES OF THE PROCESS OF REDISTRIBUTION OF SELF-OSCILLATION ENERGY UNDER THE INFLUENCE OF ATTENUATES

2019 ◽  
pp. 46-51 ◽  
Author(s):  
A. M. Konovalov ◽  
V. I. Kugushev ◽  
A. Yu. Yakovlev
Keyword(s):  
Nondestructive Testing ◽  
Small Amplitude ◽  
Rectangular Cross Section ◽  
Experimental Studies ◽  
Energy Redistribution ◽  
Damping Effect ◽  
Highly Sensitive ◽  
Oscillation Energy ◽  
Split Mode ◽  
The Given

Below given are the results of experimental studies of the process of damping of self-oscillation of the beam which is a long plate with rectangular cross-section. The studies were aimed at demonstration of the process (accompanying the damping) of energy redistribution between the modes and harmonics of self-oscillations under the conditions when this energy is essentially bounded. The artificial damper was used which was a small-size slightly pressed plate. The same local damping effect is created by cracks in the parts when there are oscillations, plastic deformation at the apex of crack. Specially developed transducers operating in split mode as part of multifunction acoustic impedance fault detector were used as measuring equipment. The receiver-transducer was attached at the end of the beam, the generator-transducer was attached at the centre of the beam so as to induce oscillation train consisting of five dominant flexural modes of self-oscillations of the beam. Limitation of energy inducing self-oscillations was determined by the rigidity of spring-plates of generator-transducer. The rigidity of the plates was chosen so as oscillation energy was sufficient only for extraction of the given train amplitudes as being dominant, whereas the rest modes of self-oscillations were either not induced at all or were induced with small amplitude. It is demonstrated that redistribution process, when inducing energy is limited, is highly sensitive to attenuants, which allows to use it as a crack indicator during integral nondestructive testing of parts and entire assemblies. For this reason it is concluded that the process of energy redistribution between different harmonics and modes of self-oscillations under the influence of damping factors is advanced for computer-aided nondestructive testing.

scholarly journals Semantic Segmentation of High-Resolution Airborne Images With Dual-Stream DeepLabV3+

2021 ◽  
Vol 11 (1) ◽  
pp. 23
Author(s):  
Ozgun Akcay ◽  
Ahmet Cumhur Kinaci ◽  
Emin Ozgur Avsar ◽  
Umut Aydar
Keyword(s):  
Data Augmentation ◽  
Contextual Information ◽  
Imbalanced Data ◽  
Semantic Segmentation ◽  
Multi Scale ◽  
Segmentation Algorithms ◽  
Geographic Datasets ◽  
Stream Architecture ◽  
The Given

In geospatial applications such as urban planning and land use management, automatic detection and classification of earth objects are essential and primary subjects. When the significant semantic segmentation algorithms are considered, DeepLabV3+ stands out as a state-of-the-art CNN. Although the DeepLabV3+ model is capable of extracting multi-scale contextual information, there is still a need for multi-stream architectural approaches and different training approaches of the model that can leverage multi-modal geographic datasets. In this study, a new end-to-end dual-stream architecture that considers geospatial imagery was developed based on the DeepLabV3+ architecture. As a result, the spectral datasets other than RGB provided increments in semantic segmentation accuracies when they were used as additional channels to height information. Furthermore, both the given data augmentation and Tversky loss function which is sensitive to imbalanced data accomplished better overall accuracies. Also, it has been shown that the new dual-stream architecture using Potsdam and Vaihingen datasets produced 88.87% and 87.39% overall semantic segmentation accuracies, respectively. Eventually, it was seen that enhancement of the traditional significant semantic segmentation networks has a great potential to provide higher model performances, whereas the contribution of geospatial data as the second stream to RGB to segmentation was explicitly shown.

UV Spectrophotometric Method Development and Validation of Carbimazole in Bulk and Tablet Dosage form

2021 ◽  
pp. 163-166
Author(s):  
Zainab A. Bagalkote ◽  
Ganesh Gajeli
Keyword(s):  
Spectrophotometric Method ◽  
Dosage Form ◽  
Method Development ◽  
Uv Spectrum ◽  
Highly Sensitive ◽  
Method Development And Validation ◽  
Uv Visible ◽  
Development And Validation ◽  
Tablet Dosage ◽  
The Given

Objective: A new, simple, sensitive, precise, reproducible UV visible spectrophotometric method was developed for the estimation of Carbimazole in Tablet dosage form. Methods: The UV spectrum of Carbimazole in methanol and distilled water (30:70) showed λ max at 289.6nm. Beer’s law is valid in the concentration range of 10-50µg/ml. This method was validated for linearity, accuracy, precision, ruggedness and robustness. Results: The method has demonstrated excellent linearity over the range of 10-50µg/ml with the regression equation y = 0.0232x + 0.0466, and regression coefficient i.e, r2= 0.9992 moreover, the method was found to be highly sensitive with LOD (1.818µg/ml) and LOQ (5.509µg/ml). Conclusion: From the results it can be concluded that the given method can be successfully applied for assay of Carbimazole in Tablet dosage form.

scholarly journals Speech Recognition for Task Domains with Sparse Matched Training Data

2020 ◽  
Vol 10 (18) ◽  
pp. 6155
Author(s):  
Byung Ok Kang ◽  
Hyeong Bae Jeon ◽  
Jeon Gue Park
Keyword(s):  
Speech Recognition ◽  
Active Learning ◽  
Latent Variables ◽  
Data Augmentation ◽  
Integrated System ◽  
Training Data ◽  
Target Domain ◽  
Teacher Student ◽  
Speech Data ◽  
Active Learning Method

We propose two approaches to handle speech recognition for task domains with sparse matched training data. One is an active learning method that selects training data for the target domain from another general domain that already has a significant amount of labeled speech data. This method uses attribute-disentangled latent variables. For the active learning process, we designed an integrated system consisting of a variational autoencoder with an encoder that infers latent variables with disentangled attributes from the input speech, and a classifier that selects training data with attributes matching the target domain. The other method combines data augmentation methods for generating matched target domain speech data and transfer learning methods based on teacher/student learning. To evaluate the proposed method, we experimented with various task domains with sparse matched training data. The experimental results show that the proposed method has qualitative characteristics that are suitable for the desired purpose, it outperforms random selection, and is comparable to using an equal amount of additional target domain data.

scholarly journals THE DEVELOPMENT OF TEST SYSTEMS FOR DETERMINING THE EXPRESSION OF THE BIRC5 AND HER-2/NEU GENES IN LABORATORY ANIMALS USING PCR WITH FLUORESCENCE DETECTION AND EVALUATION OF THEIR EFFECTIVENESS

2021 ◽  
Vol 20 (2) ◽  
pp. 65-70
Author(s):  
V.M. Semenov ◽  
◽  
V.V. Pabiarzhyn ◽  
E.S. Pashinskaya ◽  
S.K. Egorov ◽  
...  
Keyword(s):  
Fluorescence Detection ◽  
Detection Method ◽  
Test System ◽  
Fluorescent Detection ◽  
Laboratory Animals ◽  
Test Systems ◽  
Highly Sensitive ◽  
Her 2 ◽  
The Given ◽  
Pcr Test

Objectives. To develop primers and probes for detecting the expression of the BIRC5 and HER-2/neu genes and to optimize the reactions with the subsequent creation of PCR test systems with a fluorescent detection method. Material and methods. Achieving this goal included 5 stages, as a result of which two test systems were developed to determine the expression of the BIRC5 and HER-2/neu genes by real-time PCR in the experiment. Results. Two test systems for determining the expression of the BIRC5 and HER-2/neu genes in laboratory animals by means of PCR with fluorescence detection have been developed, that are highly sensitive and effective. Conclusions. The developed test system can be used for determining changes in the expression of the given genes during experiments of biological, veterinary and medical profiles.

Sign in / Sign up

Export Citation Format

Share Document