scholarly journals Automatic Processing Pipeline for Collecting and Annotating Air-Traffic Voice Communication Data

2021 ◽  
Vol 2 (1) ◽  
Author(s):  
Martin Kocour ◽  
Karel Veselý ◽  
Igor Szöke ◽  
Santosh Kesiraju ◽  
Juan Zuluaga-Gomez ◽  
...  

This document describes our pipeline for automatic processing of ATCO pilot audio communication we developed as part of the ATCO2 project. So far, we collected two thousand hours of audio recordings that we either preprocessed for the transcribers or used for semi-supervised training. Both methods of using the collected data can further improve our pipeline by retraining our models. The proposed automatic processing pipeline is a cascade of many standalone components: (a) segmentation, (b) volume control, (c) signal-to-noise ratio filtering, (d) diarization, (e) ‘speech-to-text’ (ASR) module, (f) English language detection, (g) call-sign code recognition, (h) ATCO—pilot classification and (i) highlighting commands and values. The key component of the pipeline is a speech-to-text transcription system that has to be trained with real-world ATC data; otherwise, the performance is poor. In order to further improve speech-to-text performance, we apply both semi-supervised training with our recordings and the contextual adaptation that uses a list of plausible callsigns from surveillance data as auxiliary information. Downstream NLP/NLU tasks are important from an application point of view. These application tasks need accurate models operating on top of the real speech-to-text output; thus, there is a need for more data too. Creating ATC data is the main aspiration of the ATCO2 project. At the end of the project, the data will be packaged and distributed by ELDA.

2019 ◽  
Vol 16 (2-3) ◽  
pp. 161-179
Author(s):  
Outi Paloposki

The article looks at book production and circulation from the point of view of translators, who, as purchasers and readers of foreign-language books, are an important mediating force in the selection of literature for translation. Taking the German publisher Tauchnitz's series ‘Collection of British Authors’ and its circulation in Finland in the nineteenth and early twentieth century as a case in point, the article argues that the increased availability of English-language books facilitated the acquiring and honing of translators' language skills and gradually diminished the need for indirect translating. Book history and translation studies meet here in an examination of the role of the Collection in Finnish translators' work.


2020 ◽  
Vol 4 (2) ◽  
pp. 118-129
Author(s):  
Asti Gumartifa ◽  
◽  
Indah Windra Dwie Agustiani

Gaining English language learning effectively has been discussed all years long. Similarly, Learners have various troubles outcomes in the learning process. Creating a joyful and comfortable situation must be considered by learners. Thus, the implementation of effective learning strategies is certainly necessary for English learners. This descriptive study has two purposes: first, to introduce the classification and characterization of learning strategies such as; memory, cognitive, metacognitive, compensation, social, and affective strategies that are used by learners in the classroom and second, it provides some questionnaires item based on Strategy of Inventory for Language Learning (SILL) version 5.0 that can be used to examine the frequency of students’ learning strategies in the learning process. The summary of this study explains and discusses the researchers’ point of view on the impact of learning outcomes by learning strategies used. Finally, utilizing appropriate learning strategies are certainly beneficial for both teachers and learners to achieve the learning target effectively.


2019 ◽  
pp. 87-95

The article is devoted to the role of Tourism terminology in linguistics and the issue of general classification, peculiarities in the expression and translation of terms related to tourism in English into Uzbek and Russian, as well as the choice of the most optimal methods for translating terms in accordance with the requirements of this professional sphere. The terminology of the English language tourism is distinguished by its brightness, versatility. Tourism terms are formed under the influence of a generalized lexical layer of language and perform a specific functional function.Tourism terms are formed through the affixation method (prefixation, suffixation, circumphixation) and get rich through the process.The terminology of English Tourism is distinguished by its content and structural features, forming a part of the language vocabulary from the linguistic point of view. Texts in the field of Tourism take into their composition concepts of Tourism and interpret them in their content. They will be mainly in the form of advertising, as well as enlighten information about a particular region or place, create informational precedents and ensure their manifestation in the social cultural presence. The relevance of the study of the problems of translation of terms in the field of tourism has been investigated, mainly due to the development of international relations, expansion of cooperation between local and foreign companies, as well as the increase in this area of communication.


Geophysics ◽  
1997 ◽  
Vol 62 (4) ◽  
pp. 1226-1237 ◽  
Author(s):  
Irina Apostoiu‐Marin ◽  
Andreas Ehinger

Prestack depth migration can be used in the velocity model estimation process if one succeeds in interpreting depth events obtained with erroneous velocity models. The interpretational difficulty arises from the fact that migration with erroneous velocity does not yield the geologically correct reflector geometries and that individual migrated images suffer from poor signal‐to‐noise ratio. Moreover, migrated events may be of considerable complexity and thus hard to identify. In this paper, we examine the influence of wrong velocity models on the output of prestack depth migration in the case of straight reflector and point diffractor data in homogeneous media. To avoid obscuring migration results by artifacts (“smiles”), we use a geometrical technique for modeling and migration yielding a point‐to‐point map from time‐domain data to depth‐domain data. We discover that strong deformation of migrated events may occur even in situations of simple structures and small velocity errors. From a kinematical point of view, we compare the results of common‐shot and common‐offset migration. and we find that common‐offset migration with erroneous velocity models yields less severe image distortion than common‐shot migration. However, for any kind of migration, it is important to use the entire cube of migrated data to consistently interpret in the prestack depth‐migrated domain.


1994 ◽  
Vol 04 (02) ◽  
pp. 441-446 ◽  
Author(s):  
V.S. ANISHCHENKO ◽  
M.A. SAFONOVA ◽  
L.O. CHUA

Using numerical simulation, we establish the possibility of realizing the stochastic resonance (SR) phenomenon in Chua’s circuit when it is excited by either an amplitude-modulated or a frequency-modulated signal. It is shown that the application of a frequency-modulated signal to a Chua’s circuit operating in a regime of dynamical intermittency is preferable over an amplitude-modulated signal from the point of view of minimizing the signal distortion and maximizing the signal-to-noise ratio (SNR).


2018 ◽  
Vol 42 (1) ◽  
pp. 167-174 ◽  
Author(s):  
V. I. Parfenov ◽  
D. Y. Golovanov

An algorithm for estimating time positions and amplitudes of a periodic pulse sequence from a small number of samples was proposed. The number of these samples was determined only by the number of pulses. The performance of this algorithm was considered on the assumption that the spectrum of the original signal is limited with an ideal low-pass filter or the Nyquist filter, and conditions for the conversion from one filter to the other were determined. The efficiency of the proposed algorithm was investigated through analyzing in which way the dispersion of estimates of time positions and amplitudes depends on the signal-to-noise ratio and on the number of pulses in the sequence. It was shown that, from this point of view, the efficiency of the algorithm decreases with increasing number of sequence pulses. Besides, the efficiency of the proposed algorithm decreases with decreasing signal-to-noise ratio.It was found that, unlike the classical maximum likelihood algorithm, the proposed algorithm does not require a search for the maximum of a multivariable function, meanwhile characteristics of the estimates are practically the same for both these methods. Also, it was shown that the estimation accuracy of the proposed algorithm can be increased by an insignificant increase in the number of signal samples.The results obtained may be used in the practical design of laser communication systems, in which the multipulse pulse-position modulation is used for message transmission. 


2019 ◽  
Author(s):  
Jamal Kaid Mohammed Ali ◽  
S. Imtiaz Hasnain ◽  
M. Salim Beg

Overindulgence in social networking, in general, and texting, in particular, is much in practice. It is cutting across various population boundaries and has almost assumed an endemic proportion. Its consequential impact on the standard language has acquired greater importance. This paper aims to determine the perceptions and attitudes of English Second Language (ESL) learners at Aligarh Muslim University towards the consequences of texting on Standard English. The data were collected through a five-point scale questionnaire from ninety students who were enrolled at Aligarh Muslim University during the academic year 2010-2011. The respondents completed a 16-item questionnaire. The students from which the data were collected were grouped according to their levels. The results indicate the negative impact of this new usage of the language in breaking the rules of English language and influencing their literacy. Moreover, the questionnaire results from respondents' point of view show that regardless of their heavy use of texting, most respondents have a negative attitude towards texting and they viewed it as a threat to Standard English.


2020 ◽  
Vol 224 ◽  
pp. 72-79
Author(s):  
E.V. Bessonova ◽  
◽  
I.K. Kirillova ◽  
YU.A. Tarabarina ◽  
◽  
...  

Today experts with a high level of proficiency in a foreign language are considered in demand in the labour market. The level of foreign language proficiency is confirmed by a high test result of international exams in a foreign language. The essay is a mandatory part of international English language exams such as TOEFL, IELTS, and Cambridge Advanced English. We examined the requirements and assessment criteria for the essay writing exam task. The task assesses the level of speech skills formation necessary to create your own pieces of writing in a foreign language. As part of the research, we developed a technology for teaching writing based on a product-oriented approach. According to the technology we have identified the following stages of text production: task orientation, text planning, text writing, and text self-editing. We have also proposed a set of exercises aimed at developing following skills: task understanding, formulating the author’s point of view and its proving with relevant examples, planning a cohesive and coherent text, text division into paragraphs, highlighting of the paragraph’s main idea, development of the idea in the text, expressing ideas in the text logically in accordance with the rhetorical structure of English essay, usage of lexical cohesive means, text self-editing. This technology was tested during experimental training; its results prove the effectiveness of the proposed technology for teaching essay writing according to international English language exams requirements.


Author(s):  
Эльмира Рафаилевна Ибрагимова

В данной статье анализируются высказывания из национальных лингвистических корпусов татарского и английского языков с точки зрения возможности их номинализации посредством наименований лица, включенных в состав данных высказываний. Рассмотрены как традиционно выделяемые типы номинализации - события, факта, пропозиции, так и номинализация посредством наименования лица как периферийный тип. Установлено, что как английское, так и татарское номинативное предложение не выполняет по отношению к называемому одушевленному лицу функции субституции и конкретное наименование лица, выражая признак, обладает лишь предикативной референцией. Выявлены сходства и различия в функционировании наименований лица как средства номинализации в английских и татарских высказываниях. Сделаны выводы о том, что в английском языке автономное функционирование наименования лица как отдельного предложения возможно только в разговорной речи. В стилистически нейтральных высказываниях английского языка всегда имеет место глагол. В татарском языке оценка может выражаться как наименованием лица, так и прилагательным. В обоих языках достаточно частотными являются наименования лица, образованные от имен прилагательных путем инверсии. И в английском, и в татарском языках исследуемые примеры довольно часто содержат сопровождающее местоимение второго лица. This article analyzes the statements from the national linguistic corpus of the Tatar and English languages from the point of view of their nominalization potential by means of the person names in these above-mentioned statements. The author considered both the traditionally distinguished types of nominalization (events, facts, propositions) and nominalization by the person name as a peripheral type. It has been established that both the English and Tatar nominative sentences do not fulfill the function of substitution in relation to the named animate person, and the specific person name expressing the feature has only a predicative reference. The similarities and differences in the functioning of the person names as the means of nominalization in English and Tatar expressions have been revealed. The author concluded that in English the autonomous functioning of the person name as a separate sentence is possible only in colloquial speech. In stylistically neutral expressions of the English language, a verb always occurs. In the Tatar language, the assessment can be expressed both by the person name and by the adjective. In both languages, the person names formed from adjectives by means of inversion are quite frequent. In both the English and Tatar languages, the studied examples quite often contain an accompanying second person pronoun


2021 ◽  
Vol 9 ◽  
Author(s):  
Zahra Sobhani ◽  
Yunlong Luo ◽  
Christopher T. Gibson ◽  
Youhong Tang ◽  
Ravi Naidu ◽  
...  

As an emerging contaminant, microplastic is receiving increasing attention. However, the contamination source is not fully known, and new sources are still being identified. Herewith, we report that microplastics can be found in our gardens, either due to the wrongdoing of leaving plastic bubble wraps to be mixed with mulches or due to the use of plastic landscape fabrics in the mulch bed. In the beginning, they were of large sizes, such as > 5 mm. However, after 7 years in the garden, owing to natural degradation, weathering, or abrasion, microplastics are released. We categorize the plastic fragments into different groups, 5 mm–0.75 mm, 0.75 mm–100 μm, and 100–0.8 μm, using filters such as kitchenware, meaning we can collect microplastics in our gardens by ourselves. We then characterized the plastics using Raman image mapping and a logic-based algorithm to increase the signal-to-noise ratio and the image certainty. This is because the signal-to-noise ratio from a single Raman spectrum, or even from an individual peak, is significantly less than that from a spectrum matrix of Raman mapping (such as 1 vs. 50 × 50) that contains 2,500 spectra, from the statistical point of view. From the 10 g soil we sampled, we could detect the microplastics, including large (5 mm–100 μm) fragments and small (<100 μm) ones, suggesting the degradation fate of plastics in the gardens. Overall, these results warn us that we must be careful when we do gardening, including selection of plastic items for gardens.


Sign in / Sign up

Export Citation Format

Share Document