Abstract--In a distributed speech recognition (DSR) framework, the speech features are quantized and compressed at the client and recognized at the server. However, recognition acc...
Recently various techniques to improve the correlation model of feature vector elements in speech recognition systems have been proposed. Such techniques include semi-tied covaria...
In this paper we discuss the design, acquisition and preprocessing of a Czech audio-visual speech corpus. The corpus is intended for training and testing of existing audio-visual ...
entional user behavior, we need a principled mannerAbstract for relaxing contextual constraints when they are violated.When computer speech recognition is used for problem In order...
Sheryl R. Young, Wayne H. Ward, Alexander G. Haupt...
In this paper we describe and analyze a data pruning method in combination with template-based automatic speech recognition. We demonstrate the positive effects of polishing the t...