Traditional n-gram language models are widely used in state-of-the-art large vocabulary speech recognition systems. This simple model suffers from some limitations, such as overfi...
Abstract— Especially for tasks like automatic meeting transcription, it would be useful to automatically recognize speech also while multiple speakers are talking simultaneously....
Dorothea Kolossa, Shoko Araki, Marc Delcroix, Tomo...
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...
We present a system for model-based source separation for use on single channel speech mixtures where the precise source characteristics are not known a priori. The sources are mo...
Log-linear models have recently been used in acoustic modeling for speech recognition systems. This has been motivated by competitive results compared to systems based on Gaussian...