Tobias Schrank

Learn More
Robust automatic speech recognition in adverse environments is a challenging task. We address the 4 CHiME challenge [1] multi-channel tracks by proposing a deep eigenvector beamformer 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)
Uncertainty is ubiquitous in natural human communication. Human listeners assess the speaker’s degree of uncertainty at any time in communication and use this information to shape dialogue. In contrast, currently available computer systems dealing with spoken language are usually not built to perform this task. The ability to detect uncertainty would likely(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)
  • 1