As improvements on acoustic modeling have rapidly progressed in recent years thanks to the impressive gains in performance obtained using deep neural networks (DNNs), language modeling remains a bottleneck for high performance large vocabulary continuous speech recognition (LVCSR) systems. In this paper an algorithm for automatic words extraction from a stream of phones is suggested to be used in a dictionary-based LVCSR system, to overcome the limitations of current LVCSR systems. Experimental results show the effectiveness of this approach.
展开▼