Improved acoustic modeling can significantly decrease the error rate in large-vocabulary speech recognition. Our approach to the problem is twofold. We first propose a scheme that...
This paper presents a novel probabilistic approach to speech enhancement. Instead of a deterministic logarithmic relationship, we assume a probabilistic relationship between the fr...
We investigate genre effects on the task of automatic sentence segmentation, focusing on two important domains – broadcast news (BN) and broadcast conversation (BC). We employ a...
Semi-continuous acoustic models, where the output distributions for all Hidden Markov Model states share a common codebook of Gaussian density functions, are a well-known and prov...
This paper gives an overview of an architecture and search organization for large vocabulary, continuous speech recognition (LVCSR at RWTH). In the rst part of the paper, we descri...
Stefan Ortmanns, Lutz Welling, Klaus Beulen, Frank...