DocumentCode :
175633
Title :
Improved mandarin spoken term detection by using deep neural network for keyword verification
Author :
Xuyang Wang ; Ta Li ; Yeming Xiao ; Jielin Pan ; Yonghong Yan
Author_Institution :
Key Lab. of Speech Acoust. & Content Understanding, Beijing, China
fYear :
2014
fDate :
19-21 Aug. 2014
Firstpage :
144
Lastpage :
148
Abstract :
In this paper, we propose to use Deep Neural Network (DNN), which has been proved to be the state-of-the-art technique in speech recognition, to re-estimate the confidence of keyword hypotheses in the verification stage of spoken term detection. The speech recognition system based on DNN outperforms that based on conventional Gaussian Mixture Model (GMM) but suffers from the increased decoding time. When the speed of decoding or indexing is critical, it seems to be a trade-off between the performance and the speed to utilize DNN in keyword verification. Inspired by the utilization and acceleration of DNN in the decoding stage, we explored an efficient method to replace GMM by DNN in the verification stage. 5% relative reduction of equal error rate (EER) is achieved and the improvement of recall in the high precision region is especially significant, which is essential to practical tasks. Meanwhile, the search time decreases more than 50% compared to the time derived from the verification on DNN without any refinements.
Keywords :
Gaussian processes; mixture models; natural languages; neural nets; speech recognition; DNN; EER; Gaussian mixture model; Mandarin spoken term detection; deep neural network; equal error rate; keyword verification; speech recognition; Acoustics; Decoding; Hidden Markov models; Lattices; Neural networks; Speech; Speech recognition;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Natural Computation (ICNC), 2014 10th International Conference on
Conference_Location :
Xiamen
Print_ISBN :
978-1-4799-5150-5
Type :
conf
DOI :
10.1109/ICNC.2014.6975825
Filename :
6975825
Link To Document :
بازگشت