Felix Schneider

Sofi Esterhazy, Felix Schneider, Ilario Mazzieri et al.

Motivated by the need to detect an underground cavity within the procedure of an On-Site-Inspection (OSI), of the Comprehensive Nuclear Test Ban Treaty Organization, the aim of this paper is to present results on the comparison of our numerical simulations with an analytic solution. The accurate numerical modeling can facilitate the development of proper analysis techniques to detect the remnants of an underground nuclear test. The larger goal is to help set a rigorous scientific base of OSI and to contribute to bringing the Treaty into force. For our 3D numerical simulations, we use the discontinuous Galerkin Spectral Element Code SPEED jointly developed at MOX (The Laboratory for Modeling and Scientific Computing, Department of Mathematics) and at DICA (Department of Civil and Environmental Engineering) of the Politecnico di Milano.

Felix Schneider, Marco Turchi, Alex Waibel

With more and more meetings moving to a digital domain, meeting summarization has recently gained interest in both academic and commercial research. However, prior academic research focuses on meeting summarization as an offline task, performed after the meeting concludes. In this paper, we perform the first systematic study of online meeting summarization. For this purpose, we propose several policies for conducting online summarization. We discuss the unique challenges of this task compared to the offline setting and define novel metrics to evaluate latency and partial summary quality. The experiments on the AutoMin dataset show that 1) online models can produce strong summaries, 2) our metrics allow a detailed analysis of different systems' quality-latency trade-off, also taking into account intermediate outputs and 3) adaptive policies perform better than fixed scheduled ones. These findings provide a starting point for the wider research community to explore this important task.

Dominik Macháček, Jonáš Kratochvíl, Sangeet Sagar et al.

This paper is an ELITR system submission for the non-native speech translation task at IWSLT 2020. We describe systems for offline ASR, real-time ASR, and our cascaded approach to offline SLT and real-time SLT. We select our primary candidates from a pool of pre-existing systems, develop a new end-to-end general ASR system, and a hybrid ASR trained on non-native speech. The provided small validation set prevents us from carrying out a complex validation, but we submit all the unselected candidates for contrastive evaluation on the test set.