Alex Waibel
Karlsruhe Institute of Technology
719 Papers
9.9K Citations
Alex Waibel is an academic researcher from Karlsruhe Institute of Technology. The author has contributed to research in topics: Machine translation & Computer science. The author has an hindex of 79, co-authored 690 publications. Previous affiliations of Alex Waibel include Carnegie Mellon University & University of Pittsburgh.
Chat about Author
Papers
Self-Attentional Acoustic Models
Matthias Sperber,Jan Niehues,Graham Neubig,Sebastian Stüker,Alex Waibel +4 more
- 02 Sep 2018
TL;DR: In this article, the authors apply self-attention to acoustic modeling, and propose a Gaussian biasing approach that allows explicit control over the context range, and demonstrate that interpretability is a strength of selfattentional acoustic models.
164
Gaze Tracking Based on Face‐Color
Bernt Schiele,Alex Waibel +1 more
- 01 Jan 1995
TL;DR: The gaze-tracking system, uses several connectionist modules, that track a person's face using a software controlled pan-tilt camera with zoom and identiies the focus of attention from the orientation and direction of the face.
158
Strategies for automatic segmentation of audio data
Thomas Kemp,Maria Schmidt,Martin Westphal,Alex Waibel +3 more
- 05 Jun 2000
TL;DR: In this paper, three different segmenting strategies are compared on the same broadcast news test data and it is shown that model-based and metric-based techniques outperform the simpler energy-based algorithms.
Enabling Multimodal Human–Robot Interaction for the Karlsruhe Humanoid Robot
Rainer Stiefelhagen,Hazim Kemal Ekenel,Christian Fügen,Petra Gieselmann,Hartwig Holzapfel,Florian Kraft,Kai Nickel,Michael Voit,Alex Waibel +8 more
TL;DR: The systems for spontaneous speech recognition, multimodal dialogue processing, and visual perception of a user, which includes localization, tracking, and identification of the user, recognition of pointing gestures, as well as the recognition of a person's head orientation are presented.
157
•Proceedings Article
Towards Continuous Speech Recognition Using Surface Electromyography
Szu-Chen Stan Jou,Tanja Schultz,Matthias Walliczek,Florian Kraft,Alex Waibel +4 more
- 01 Jan 2006
TL;DR: This paper demonstrates how to train the phoneme-based acoustic models with carefully designed electromyographic feature extraction methods by decomposing the signal into different feature space and successfully keep the useful information while reducing the noise.
156