- Full text PDF available (5)
- This year (0)
- Last five years (1)
We present a universal approach to uncover and correct systematic local errors in complex speech-to-text systems. Whereas previous work to minimize speech recognition errors mostly relies on N-best lists or word lattices, our approach is merely based on the first-best system output. The paradigm of Transformation-Based Learning (TBL) is adapted from… (More)
BACKGROUND Major trauma remains one of the principle causes of disability and death throughout the world. There is currently no satisfactory risk assessment to predict mortality in patients with major trauma. The aim of our study is to examine whether S-100 B protein concentrations correlate with injury severity and survival in patients with major trauma,… (More)
This article presents an evolutionary algorithm (EA) for the capacitated minimum spanning tree problem occurring in telecom-munication applications. The EA encodes a solution by a predecessor vector indicating for each node the preceding node at the path to the given central root node. Initializa-tion, crossover, and mutation operators were specifically… (More)
alltäglichen Aufgaben davon profitieren.
Automatic speech recognition (ASR) has become a valuable tool in large document production environments like medical dictation. While manual post-processing is still needed for correcting speech recognition errors and for creating documents which adhere to various stylistic and formatting conventions, a large part of the document production process is… (More)