Johannes Stahl

Learn More
A common problem in radiology teleconferencing is the difficulty of transmitting a large volume of data over communication channels with a relatively low bandwidth. Although videoconferencing systems are easily implemented, they generally require lossy image compression, which can lead to significantly altered findings. A teleconsultation and(More)
PURPOSE A novel rotational IMRT (rIMRT) technique using burst delivery (continuous gantry rotation with beam off during MLC repositioning) is investigated. The authors evaluate the plan quality and delivery efficiency and accuracy of this dynamic technique with a conventional flat 6 MV photon beam. METHODS Burst-delivery rIMRT was implemented in a(More)
Conventional automatic speech recognition (ASR) often neglects the spectral phase information in its front-end and feature extraction stages. The aim of this paper is to show the impact that enhancement of the noisy spectral phase has on ASR accuracy when dealing with speech signals corrupted with additive noise. Apart from proof-of-concept experiments(More)
he world's ecosystems provide environmental services we simply cannot live without. As an integral part of nature, our fate is tightly linked with biological diversity, i.e. the huge variety of animals, plants and microorganisms that live in mountains, forests, oceans, wetlands and other ecosystems. We rely on this diversity of life to provide us with(More)
Robust automatic speech recognition in adverse environments is a challenging task. We address the 4 th CHiME challenge [1] multi-channel tracks by proposing a deep eigenvector beam-former as front-end. To train the acoustic models, we propose to supplement the beamformed data by the noisy audio streams of the individual microphones provided in the real set.(More)