ELITR: European Live Translator

2021

This paper presents an automatic speech translation system aimed at live subtitling of conference presentations. We describe the overall architecture and key processing components. More importantly, we explain our strategy for building a complex system for end-users from numerous individual components, each of which has been tested only in laboratory conditions. The system is a working prototype that is routinely tested in recognizing English, Czech, and German speech and presenting it translated simultaneously into 42 target languages.

2020

This paper presents our progress towards deploying a versatile communication platform in the task of highly multilingual live speech translation for conferences and remote meetings live subtitling. The platform has been designed with a focus on very low latency and high flexibility while allowing research prototypes of speech and text processing tools to be easily connected, regardless of where they physically run. We outline our architecture solution and also briefly compare it with the ELG platform. Technical details are provided on the most important components and we summarize the test deployment events we ran so far.

1999

In this paper we report on the ongoing activity for the project ESPRIT LTR EuTrans during the first year. Issues for the Fondazione Ugo Bordoni (FUB) have been the prototype implementation, the text and speech data collection and the usability assessment. The corpus has two main objectives: to provide training material for recognition and translation training; to contain speech material for acoustic modelling, and textual material for language modelling and translation modelling. The main aim of the project is to show the potentialities of an Example Based approach to the Machine Translation for a speech-to-speech application in the domain of hotel reservation. The speech application envisaged is a telephone communication media between two human beings (the customer and the receptionist) with translation abilities: the customer call, from inside or outside, a special number of the hotel, speak in his/her own language in order to make a reservation, to cancel a reservation, to ask information for services, to claim for services; the receptionist will receive the customer request in his/her own language and will answer in his/her language through the same media. The application has been simulated through the technique of Wizard of Oz; the current prototype is based on a two-machine architecture: a recognition/translation server and client supporting the telephone interface towards the user and the GUI towards the receptionist. The WoZ plays the role of the receptionist.

2017

Making audiovisual educational material accessible for non-native speakers and people who are deaf or hard-of-hearing is an ongoing challenge and the state-of-the-art in this field shows that no current software provides a fully automatic, high-quality solution. This article presents Miro Translate, a hybrid intralinguistic subtitling tool developed in response to this challenge by the Miro Programme at the University of Perpignan Via Domitia. This cloud-based solution integrates the automatic speech recognition (ASR) technology provided by the Microsoft Translator Speech API to generate automatic captions. It also incorporates a set of editing functionalities to provide a readable and legible target output that complies with subtitling conventions. In conclusion, the aim of Miro Translate is to produce a costefficient solution that meets the increasing demand for high quality captions in instructional video.

2000

The EUTRANS project aims at using example-based approaches for the automatic development of Machine Translation systems accepting text and speech input for limited-domain applications. During the first phase of the project, a speech-translation system that is based on the use of automatically learned subsequential transducers has been built. This paper contains a detailed and mostly self-contained overview of the transducer-learning algorithms and system architecture, along with a new approach for using categories representing words or short phrases in both input and output languages. Experimental results using this approach are reported for a task involving the recognition and translation of sentences in the hotel-reception communication domain, with a vocabulary of 683 words in Spanish. A translation word-error rate of 1.97% is achieved in real-time factor 2.7 on a Personal Computer.

2017

For the past 39 years the international conference, Translating and the Computer (TC), has been a unique forum for academics, users, developers and vendors of translation technology tools. It is a distinctive event where translators, interpreters, researchers and business people, from translation companies, international organisations, universities and research labs, as well as freelance professionals, come together to exchange ideas and learn about the latest developments in translation technologies. Over the last two decades various translation tools such as Translation Memory programs presented at previous TC conferences, have revolutionised the work of translators. Regrettably, the same cannot be said for the work of interpreters who have yet to benefit from suitable language technology tools and resources which could assist them in their work. Given this situation, at this year's 39th TC conference we have decided to put an emphasis on the new and emerging language technologies, tools and resources which can support the work of interpreters. The panel 'New Frontiers in Interpreting Technology' features leading experts and practitioners in interpreting and the TC39 programme offers several talks presenting tools for interpreters. We firmly believe that the presentations and discussions on this topic will encourage the development of innovative tools which will revolutionise the work of interpreters in the near future, as has already been the case for translators. This year's conference also features stimulating talks on Translation Technology topics central to TC conferences including but not limited to machine translation, post-editing, CAT tools and terminology. We are confident that you will find that all the presentations and posters, panels and workshops, will provide interesting user perspectives and opportunities, and will lead to inspiring discussions. We trust

2007

This paper presents the spoken language translation system developed at FBK-irst during the TC-STAR project. The system integrates automatic speech recognition with machine translation through the use of confusion networks, which permit to represent a huge number of transcription hypotheses generated by the speech recognizer. Confusion networks are efficiently decoded by a statistical machine translation system which computes the most probable translation in the target language. This paper presents the whole architecture developed for the translation of political speeches held at the European Parliament, from English to Spanish and vice versa, and at the Spanish Parliament, from Spanish to English.

Speech Technology, 2010

IRJET, 2023

For years, language has been a barrier for many companies, and people especially for companies and employees, many companies cannot extend their businesses, and many employees are not able to work in specific countries and specific companies, just because of different languages. Obstacles or issues that prevent information from flowing between a sender and a receiver cause the communication process to fail and are referred to as barriers to effective communication. If someone's words don't make sense to us, every conversation, email, report, and memo will be unproductive. Simple daily tasks might be made difficult by language limitations. As more businesses move overseas, linguistic hurdles may become a worldwide problem. This creates a hindrance in conducting business smoothly. Our project will remove language barriers in business communication worldwide, it will be advantageous for multinational companies and businesses all over the world. Our project will help to extend their business overseas without any language hindrance. Our project will be a platform where one can convert all types of text documents, audio, and video transcripts to any other language. We make use of python libraries and django for translating documents and audio files. This web application will prevent miscommunications, misunderstandings, and conflicts. It will convey thoughts, ideas, and instructions more effectively.

2000

The DIPLOMAT rapid-deployment speech translation system is intended to allow naive users to communicate across a language barrier, without strong domain restrictions, despite the errorprone nature of current speech and translation technologies. Achieving this ambitious goal depends in large part on allowing the users to interactively correct recognition and translation errors. We briefly present the Multi-Engine Machine Translation (MEMT) architecture, describing how it is wellsuited for such an application. We then describe our incorporation of interactive error correction throughout the system design. We have already developed a working bidirectional Serbo-Croatian