With increasing globalization, communication across language and cultural boundaries is becoming an essential requirement of doing business, delivering education, and providing public services. Due to the considerable cost of human translation services, only a small fraction of text documents and an even smaller percentage of spoken encounters, such as international meetings and conferences, are translated, with most resorting to the use of a common language (e.g. English) or not taking place at all. Technology may provide a potentially revolutionary way out if real-time, domain-independent, simultaneous speech translation can be realized. In this paper, we present a simultaneous speech translation system based on statistical recognition and translation technology. We discuss the technology, various system improvements and propose mechanisms for user-friendly delivery of the result. Over extensive component and end-to-end system evaluations and comparisons with human translation performance, we conclude that machines can already deliver comprehensible simultaneous translation output. Moreover, while machine performance is affected by recognition errors (and thus can be improved), human performance is limited by the cognitive challenge of performing the task in real time.

In this paper we describe a new approach to model long-range word reorderings in statistical machine translation (SMT). Until now, most SMT approaches are only able to model local reorderings. But even the word order of related languages like German and English can be very different. In recent years approaches that reorder the source sentence in a preprocessing step to better match target sentences according to POS(Part-of-Speech)-based rules have been applied successfully. We enhance this approach to model long-range reorderings by introducing discontinuous rules. We tested this new approach on a German-English translation task and could significantly improve the translation quality, by up to 0.8 BLEU points, compared to a system which already uses continuous POSbased rules to model short-range reorderings.

Abstract-This paper describes an approach for computing a consensus translation from the outputs of multiple machine translation (MT) systems. The consensus translation is computed by weighted majority voting on a confusion network, similarly to the well-established ROVER approach of Fiscus for combining speech recognition hypotheses. To create the confusion network, pairwise word alignments of the original MT hypotheses are learned using an enhanced statistical alignment algorithm that explicitly models word reordering. The context of a whole corpus of automatic translations rather than a single sentence is taken into account in order to achieve high alignment quality. The confusion network is rescored with a special language model, and the consensus translation is extracted as the best path. The proposed system combination approach was evaluated in the framework of the TC-STAR speech translation project. Up to six state-of-the-art statistical phrase-based translation systems from different project partners were combined in the experiments. Significant improvements in translation quality from Spanish to English and from English to Spanish in comparison with the best of the individual MT systems were achieved under official evaluation conditions.

For years speech translation has focused on the recognition and translation of discourses in limited domains, such as hotel reservations or scheduling tasks. Only recently research projects have been started to tackle the problem of open domain speech recognition and translation of complex tasks such as lectures and speeches. In this paper we present the on-going work at our laboratory in open domain speech translation of lectures and parliamentary speeches. Starting from a translation system for European parliamentary plenary sessions and a lecture speech recognition system we show how both components perform in unison on speech translation of lectures.

This paper presents the end-to-end evaluation of an automatic simultaneous translation system, built with state-of-the-art components. It shows whether, and for which situations, such a system might be advantageous when compared to a human interpreter. Using speeches in English translated into Spanish, we present the evaluation procedure and we discuss the results both for the recognition and translation components as well as for the overall system. Even if the translation process remains the Achilles' heel of the system, the results show that the system can keep at least half of the information, becoming potentially useful for final users.