scholarly journals Automatic recognition and representation of text in the form of audio stream

Doklady BGUIR ◽  
2021 ◽  
Vol 19 (6) ◽  
pp. 51-58
Author(s):  
L. V. Serebryanaya ◽  
I. E. Lasy

The problem of automatic speech generation from a text file is considered. An analytical review of the software has been completed. They are designed to recognize texts and convert them to an audio stream. The advantages and disadvantages of software products are estimated. Based on this, a conclusion was drawn about the relevance of developing a software for automatic generation of an audio stream from a text in Russian. Models based on artificial neural networks, which are used for speech synthesis, are analyzed. After that, a mathematical model of the created software is built. It consists of three components: a convolutional encoder, a convolutional decoder, and a transformer. The architecture of the software is designed. It includes a graphical interface, an application server, and a speech synthesis system. A number of algorithms have been developed: preprocessing text before loading it into a software, converting audio files of a training sample and training a network, generating speech based on arbitrary text files. A software has been created, which is a single-page application and has a web interface for interacting with the user. To assess the quality of the software, a metric was used that represents the average score of different opinions. As a result of the aggregation of different opinions, the metric received a sufficiently high value, on the basis of which it can be assumed that all the tasks have been solved.

2020 ◽  
Vol 4 (157) ◽  
pp. 7-11
Author(s):  
V. Zhvan ◽  
V. Donenko ◽  
S. Kulish ◽  
A. Taran

The article is devoted to the effective analysis of trench and trenchless pipeline laying technologies. In the course of the work, an analytical review of pipeline assembly was performed, the main technological parameters, the scope of each method, and their advantages and disadvantages were determined. List of considered pipeline laying methods: trenching, horizontal directional drilling, mechanical puncture, hydraulic puncture, microtunneling and punching. The article analyzes the classical trench method and the most widely used trenchless ones: horizontal directional drilling; mechanical puncture; hydraulic puncture; microtunneling; punching. Each of these methods has several advantages and disadvantages. The choice of the optimal method of laying the pipeline depends on many factors: the physical and mechanical properties of soils and hydrogeological conditions, the length and diameter of the pipeline, the presence of other communications, buildings and structures, as well as the budget that customers have. Work time is the last deciding factor. Based on the results of the analysis of pipeline laying technologies and expert survey of construction industry experts, the cost table of each method was compiled, outlining the main characteristics of the technology: length of pipeline, speed of work, scope, cost, and the advantages and disadvantages of each of the considered methods. The conclusions about the use of each of the pipeline laying methods were made. Each of the methods has its advantages and disadvantages, so to choose the method of work it is necessary to conduct a comprehensive assessment of technological parameters, cost, scope and timing of work. The cost of lay-ing the pipeline consists of the following factors: conducting research; selection of diameter and determination of pipeline length; choice of laying method and equipment necessary for the works; selection of equipment, shut-off and control equipment and other materials arranged on the pipeline; terms of performance of works. Taking into account these factors, an estimate is made, which determines the cost of installation of a particular pipeline. After the analysis, we can conclude that among the methods of trenchless laying of pipelines can be identi-fied horizontally directional drilling, it is this method of laying the pipeline will be appropriate to use for our region. The drilling technique allows to carry out pipelines under obstacles, to pull long segments of networks, to repair site damage. This method is universal and can be used in almost any environment. Keywords: trenches, horizontal directional drilling, mechanical puncture, hydraulic piercing, microtunnelling, punching, pipeline.


2019 ◽  
Vol 26 (1) ◽  
pp. 39-62
Author(s):  
Stanislav O. Bezzubtsev ◽  
Vyacheslav V. Vasin ◽  
Dmitry Yu. Volkanov ◽  
Shynar R. Zhailauova ◽  
Vladislav A. Miroshnik ◽  
...  

The paper proposes the architecture and basic requirements for a network processor for OpenFlow switches of software-defined networks. An analysis of the architectures of well-known network processors is presented − NP-5 from EZchip (now Mellanox) and Tofino from Barefoot Networks. The advantages and disadvantages of two different versions of network processor architectures are considered: pipeline-based architecture, the stages of which are represented by a set of general-purpose processor cores, and pipeline-based architecture whose stages correspond to cores specialized for specific packet processing operations. Based on a dedicated set of the most common use case scenarios, a new architecture of the network processor unit (NPU) with functionally specialized pipeline stages was proposed. The article presents a description of the simulation model of the NPU of the proposed architecture. The simulation model of the network processor is implemented in C ++ languages using SystemC, the open-source C++ library. For the functional testing of the obtained NPU model, the described use case scenarios were implemented in C. In order to evaluate the performance of the proposed NPU architecture a set of software products developed by KM211 company and the KMX32 family of microcontrollers were used. Evaluation of NPU performance was made on the basis of a simulation model. Estimates of the processing time of one packet and the average throughput of the NPU model for each scenario are obtained.


2021 ◽  
Vol 3 (1) ◽  
pp. 29-37
Author(s):  
Y Horbachov ◽  
◽  
I Pasternak

In this project was shown software system for drug search in online mode, which was included: three services, user interface. Also, was analyzed test of this system, speed for system and efficiency of system. A software system – this is a group of integrated software tools which support certain process and share a database. This system shows how three services work: the primary service, the additional service and provider’s service. Also given are the modes of their work, their capabilities and specifically what they include and represent. The description of all technologies are given which used during development of this system, including their advantages and disadvantages in general. On the basic of this technique, the client-server system of drug search is realized. Moreover there are various options for searching for medical items, a searching by using search and by using location of the pharmacy on Google map were suggested. A description of the development environment and main of its functions were provided. In addition, what is REST API, where it was used and why exactly REST was used during development of this system. It also shows how to run the program, namely the procedure, with description, explains exactly how to run the program, and what additional plugins need to be installed. This article describes the algorithm of software system for drug search in online mode, the main functions of the system are given and described. Screenshots of the main modules of the server side and of the program are added as well as screenshots of databases.


Author(s):  
Mahbubur R. Syed ◽  
Shuvro Chakrobartty ◽  
Robert J. Bignall

Speech synthesis is the process of producing natural-sounding, highly intelligible synthetic speech simulated by a machine in such a way that it sounds as if it was produced by a human vocal system. A text-to-speech (TTS) synthesis system is a computer-based system where the input is text and the output is a simulated vocalization of that text. Before the 1970s, most speech synthesis was achieved with hardware, but this was costly and it proved impossible to properly simulate natural speech production. Since the 1970s, the use of computers has made the practical application of speech synthesis more feasible.


2003 ◽  
Vol 25 (2) ◽  
pp. 245-281 ◽  
Author(s):  
J. Clancy Clements

The advantages and disadvantages of wider or narrower definitions of pidginization and pidgin are reviewed to determine the differences between pidgins and naturalistically learned second languages (L2s). It is argued that a wider definition is preferred because it avoids problematic counterexamples and captures generalizations that allow us to view the difference between naturalistic L2 varieties and pidgins as one of degree, not of type. In first language (L1) acquisition, Bates and Goodman (1999) showed the link between the development of vocabulary and grammar and argued that this may be explained by, among other things, logical and perceptual bootstrapping. It is suggested that these types of bootstrapping are also relevant for explaining the pace of grammar development in pidgins and naturalistic L2 varieties. The tense-aspect system of a Spanish variety spoken by a Chinese immigrant in Spain is examined in detail. The data, taken from a 90-minute interview that yielded 602 tokens, reveal several clear traits of the informant's verbal system: (a) All nonfinite, imperfective verb forms (gerunds) correspond exclusively to Vendlerian activities; (b) all but three of the perfective nonfinite forms (past participles) correspond to telic verbs or predicates; and (c) 81% of the stative verbs appear in the third-person-singular present form. The sensitivity to aspectual distinctions in the informant's variety of Spanish is not addressed by logical and perceptual bootstrapping. Furthermore, although this sensitivity can be partially explained by language-specific considerations (i.e., transfer from Mandarin), such an explanation does not speak to precise form–function mappings found, which are best accounted for by appealing to the Primacy of Aspect and Distributional Bias hypotheses (Andersen, 1993; Andersen & Shirai, 1996).


2014 ◽  
Vol 955-959 ◽  
pp. 569-580 ◽  
Author(s):  
Juan Chen

The purpose of this review is to aim a summary of the development in the use of different supports for the immobilisation of a heterogeneous Fenton catalyst, which areiron-containing materials. Various anchors and immobilisation methods that are universally employed to the remediation of wastewater are considered. Commonly, the immobilisation of a heterogeneous Fenton catalyst onto supportive material has chiefly been approved through one of two major routes; chemical route physical route or physical route. The advantages and disadvantages of various immobilisation methods to obtain a gigantic surface area iron-containing materials support is considered too.


2011 ◽  
Vol 2-3 ◽  
pp. 228-233 ◽  
Author(s):  
Yang Zhang ◽  
Xin Geng ◽  
Hong Wang

A kind of stimulation device aiming at alleviating brain fag was designed. Meanwhile, the specific stereo signal which is expected to induce alpha-wave of human brain was programmed and encoded into audio files. To evaluating the effectiveness of this system, a comparison test was conducted. Volunteers are divided into control group and experimental group. Via power spectral analyzing, we can find the difference of EEG signals between control group and experimental group in alpha band (8~13Hz). It can be noted that the intensity of alpha-wave and beta-wave of experimental group is larger than that of control group obviously.


2021 ◽  
Vol 10 (3) ◽  
pp. 2961-2964
Author(s):  
S Dhole

W.H.O. declares corona virus outbreak a pandemic on 11th March, pandemic means every person on earth is prone to Covid-19. All the activities involving a large public gathering like social, educational, political, economic and many other sectors got affected School, colleges, workplaces had to be closed down temporarily to avoid further spreading of the disease. Educational programs worldwide have been affected by the COVID 19 pandemic, contributing to the almost complete closing of schools, universities, and colleges. To minimize the distribution of Covid19, several governments around the world have agreed to temporarily close educational institutions (lockdown). This is the situation that made society very panic as well as very sensitive towards mankind. The mass effect of Covid -19 can be observed in all the sectors but more poorly affected to the economical and educational sector. In the education system a great change of delivering classes from traditional mode to modern, i.e., online education though there are advantages and disadvantages of its but in the present era this is the most needful requirement of the world. Covid 19 and Academics- Advantages and Disadvantages. Though COVID-19 has created many challenges, various new streams of opportunities are also coming out. Online education has grown over the last few years and has experienced mainstream acceptance. To develop a deeper understanding of degree courses students get to control their learning environment with an online class. New models and materials of learning are always springing up in the market, Due to this various opportunities for furnishing their study. The future of online degree education looks promising and opens up education to a larger section of the population than ever before.


Sign in / Sign up

Export Citation Format

Share Document