DocumentCode
2009585
Title
The description of iFlyTek Speech Lab system for NIST2009 Language Recognition Evaluation
Author
Xu, Ying ; Song, Yan ; Long, Yan-hua ; Zhong, Hai-Bing ; Dai, Li-Rong
Author_Institution
iFlyTek Speech Lab., Univ. of Sci. & Technol. of China, Hefei, China
fYear
2010
fDate
Nov. 29 2010-Dec. 3 2010
Firstpage
157
Lastpage
161
Abstract
In this paper, we present a description of the iFlyTek Speech Lab system for NIST 2009 LRE (Language Recognition Evaluation). The system consists of acoustic systems (i.e. GMM-MMI and GMM-SVM) and phonotactic systems (i.e. PPR 4-gram LM and PPR 3-gram SVM). First, we describe several state-of-the-art techniques applied in our language recognition system, such as FA (Factor Analysis), MMI (Maximum Mutual Information), and generative and discriminative LM (Language Modelling) techniques etc. Then, we will discuss our data preprocessing techniques for handling large amount training and development data, and the mismatch among different languages, genders and channels. Finally, the evaluation results for NIST2009´s tasks and detailed analysis are given for 30, 10 and 3 seconds durations.
Keywords
speech recognition; LM; MMI; NIST2009 language recognition evaluation; acoustic systems; factor analysis; iFlyTek speech lab system; language modelling; language recognition system; maximum mutual information; phonotactic systems; state-of-the-art techniques; Acoustics; Adaptation model; Hidden Markov models; NIST; Speech; Support vector machines; Training; Acoustic Systems; Channel Compensation; NIST2009 LRE; Phonotactic System;
fLanguage
English
Publisher
ieee
Conference_Titel
Chinese Spoken Language Processing (ISCSLP), 2010 7th International Symposium on
Conference_Location
Tainan
Print_ISBN
978-1-4244-6244-5
Type
conf
DOI
10.1109/ISCSLP.2010.5684492
Filename
5684492
Link To Document