Stabilised weighted linear prediction

Stabilised weighted linear prediction - a robust all-pole method for speech processing

Weighted linear prediction (WLP) is a method to compute allpole models of speech by applying temporal weighting of the residual energy. By using short-time energy (STE) as a weighting function, the algorithm over-weight those samples that fit the underlying speech production model well. The current work introduces a modified WLP method, stabilised weighted linear prediction (SWLP) leading alway...

Weighted linear prediction for speech analysis in noisy conditions

Following earlier work, we modify linear predictive (LP) speech analysis by including temporal weighting of the squared prediction error in the model optimization. In order to focus this so called weighted LP model on the least noisy signal regions in the presence of stationary additive noise, we use shorttime signal energy as the weighting function. We compare the noisy spectrum analysis perfo...

Title: Weighted linear prediction for speech analysis in noisy conditions

Following earlier work, we modify linear predictive (LP) speech analysis by including temporal weighting of the squared prediction error in the model optimization. In order to focus this so called weighted LP model on the least noisy signal regions in the presence of stationary additive noise, we use shorttime signal energy as the weighting function. We compare the noisy spectrum analysis perfo...

Weighted Linear Matroid Parity

Weighted Linear Dynamic Logic

We introduce a weighted linear dynamic logic (weighted LDL for short) and show the expressive equivalence of its formulas to weighted rational expressions. This adds a new characterization for recognizable series to the fundamental Schützenberger theorem. Surprisingly, the equivalence does not require any restriction to our weighted LDL. Our results hold over arbitrary (resp. totally complete) ...