Language barriers present a great challenge in our increasingly connected and global world. Especially within the medical domain, e.g. hospital or emergency room, communication difficulties and delays may lead to malpractice and non-optimal patient care. In the HYKIST project, we consider patient-physician communication, more specifically between a German-speaking physician and an Arabic- or Vietnamese-speaking patient. Currently, a doctor can call the Triaphon service to get assistance from an interpreter in order to help facilitate communication. The HYKIST goal is to support the usually non-professional bilingual interpreter with an automatic speech translation system to improve patient care and help overcome language barriers. In this work, we present our ASR system development efforts for this conversational telephone speech translation task in the medical domain for two languages pairs, data collection, various acoustic model architectures and dialect-induced difficulties.

Prominently used in support vector machines and logistic regressions, kernel functions (kernels) can implicitly map data points into high dimensional spaces and make it easier to learn complex decision boundaries. In this work, by replacing the inner product function in the softmax layer, we explore the use of kernels for contextual word classification. In order to compare the individual kernels, experiments are conducted on standard language modeling and machine translation tasks. We observe a wide range of performances across different kernel settings. Extending the results, we look at the gradient properties, investigate various mixture strategies and examine the disambiguation abilities.

In this paper, we introduce a stochastic learning framework for long-term video interpolation. While most existing interpolation models require two reference frames with a short interval, our framework predicts a plausible intermediate sequence between a long interval. Our model consists of two parts: (1) a deterministic estimation to guarantee the spatial and temporal coherency among frames, (2) a stochastic sampling process to generate dynamics from inferred distributions. Experimental results show that our model is able to generate sharp and clear sequences with variations. Moreover, motions in the generated sequence are realistic and able to transfer smoothly from the referenced start frame to the end frame.