Vladimir Despotovic

Learn More
We present a semantic analysis technique for spoken input using Markov Logic Networks (MLNs). MLNs combine graphi-cal models with first-order logic. They are particularly suitable for providing inference in the presence of inconsistent and incomplete data, which are typical of an automatic speech rec-ognizer's (ASR) output in the presence of degraded(More)
In this paper, we investigate unsupervised acoustic model training approaches for dysarthric-speech recognition. These models are first, frame-based Gaussian posteriorgrams, obtained from Vector Quantization (VQ), second, so-called Acoustic Unit Descriptors (AUDs), which are hidden Markov models of phone-like units, that are trained in an unsupervised(More)
– The peaks in energy consumption arise when a number of consumers start to run within a relatively short period of time. In the case of large consumers, this can lead to an overload of the electro-energetic system. In order to avoid such scenarios, the consumers have to pay peak load additionally. The share of this cost in overall costs for electricity can(More)
Models based on linear prediction have been used for several decades in different areas of speech signal processing. While the linear approach has led to great advances in the last 40 years, it neglects nonlinearities present in the speech production mechanism. This paper compares the results of long-term nonlinear prediction based on second-order and(More)
  • 1