The paper provides an overview of the Polish Speech Database for taking dictation of legal texts, created for the purpose of LVCSR system for Polish. It presents background inform...
Grazyna Demenko, Stefan Grocholewski, Katarzyna Kl...
This paper proposes a speech comprehension computational model based on neurocognitiveresearches. The computational representation uses techniques as wavelets transform and connec...
We argue that verbal patient diagnosis is a promising application for limited-domain speech translation, and describe an architecture designed for this type of task which represen...
Manny Rayner, Pierrette Bouillon, Vol Van Dalsem I...
This paper presents an improved wavelet-based dereverberation method for automatic speech recognition (ASR). Dereverberation is based on filtering reverberant wavelet coefficients...
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...