Abstract. A representation of a three-dimensional object is autonomously learned from a sequence of the rotating object. The representation consists of single views in form of grap...
Gabriele Peters, Christian Eckes, Christoph von de...
Collecting supervised training data for automatic speech recognition (ASR) systems is both time consuming and expensive. In this paper we use the notion of virtual evidence in a g...
We present a novel OCR error correction method for languages without word delimiters that have a large character set, such as Japanese and Chinese. It consists of a statistical OC...
This paper describes our participation in the TREC-9 Spoken Document Retrieval (SDR) track. The THISL SDR system consists of a realtime version of a hybrid connectionist/HMM large...
Abstract: This paper presents a new approach for gesture classification using x- and y-projections of the image and optional depth features. The system uses a 3-D time-of-flight (T...
Eva N. K. Kollorz, Jochen Penne, Joachim Hornegger...