The paper considers some peculiarities of training and using N-gram language models with open vocabulary. It is demonstrated that explicit modeling of the probability distribution of out-of-model (unknown) words is necessary in this case. Two known techniques for this modeling are considered and a new technique with several advantages is proposed. We… (More)
This paper deals with new front-end feature improvements for Automatic Speech Recognition (ASR) robustness to changes in speech loudness. Our experiments show that applying a RASTA– like filter gives a significant improvement in robustness to speech loudness change, leading to an up to 4% PER reduction.
In this project, we solved a minimum cost flow problem derived from a simulated water supply network. The objective function was a combination of minimizing both the cost of moving water through the network, and the number of pump switches. The original water flow model was projected into a mathematical graph, and the associated minimum cost flow problem… (More)