DocumentCode :
2975069
Title :
Syntactic features for Arabic speech recognition
Author :
Kuo, Hong-Kwang Jeff ; Mangu, Lidia ; Emami, Ahmad ; Zitouni, Imed ; Lee, Young-Suk
Author_Institution :
IBM T.J. Watson Res. Center, Yorktown Heights, NY, USA
fYear :
2009
fDate :
Nov. 13 2009-Dec. 17 2009
Firstpage :
327
Lastpage :
332
Abstract :
We report word error rate improvements with syntactic features using a neural probabilistic language model through N-best re-scoring. The syntactic features we use include exposed head words and their non-terminal labels both before and after the predicted word. Neural network LMs generalize better to unseen events by modeling words and other context features in continuous space. They are suitable for incorporating many different types of features, including syntactic features, where there is no pre-defined back-off order. We choose an N-best re-scoring framework to be able to take full advantage of the complete parse tree of the entire sentence. Using syntactic features, along with morphological features, improves the word error rate (WER) by up to 5.5% relative, from 9.4% to 8.6%, on the latest GALE evaluation test set.
Keywords :
neural nets; speech recognition; Arabic speech recognition; N-best rescoring; neural network language model; neural probabilistic language model; syntactic features; word error rate; Broadcasting; Context modeling; Decoding; Error analysis; Feature extraction; Natural languages; Neural networks; Predictive models; Speech recognition; Testing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Automatic Speech Recognition & Understanding, 2009. ASRU 2009. IEEE Workshop on
Conference_Location :
Merano
Print_ISBN :
978-1-4244-5478-5
Electronic_ISBN :
978-1-4244-5479-2
Type :
conf
DOI :
10.1109/ASRU.2009.5373470
Filename :
5373470
Link To Document :
بازگشت