Abstract:
The paper describes a state-of-the-art keyword search (KWS) system in which significant improvements are obtained by using Convolutional Neural Network acoustic models, a...Show MoreMetadata
Abstract:
The paper describes a state-of-the-art keyword search (KWS) system in which significant improvements are obtained by using Convolutional Neural Network acoustic models, a two-step speech segmentation approach and a simplified ASR architecture optimized for KWS. The system described in this paper had the best performance in the 2013 DARPA RATS evaluation for both Levantine and Farsi.
Date of Conference: 08-12 December 2013
Date Added to IEEE Xplore: 09 January 2014
Electronic ISBN:978-1-4799-2756-2