DocumentCode :
36457
Title :
Spoken Language Recognition With Prosodic Features
Author :
Ng, Raymond W. M. ; Tan Lee ; Cheung-Chi Leung ; Bin Ma ; Haizhou Li
Author_Institution :
Dept. of Electron. Eng., Chinese Univ. of Hong Kong, Shatin, China
Volume :
21
Issue :
9
fYear :
2013
fDate :
Sept. 2013
Firstpage :
1841
Lastpage :
1853
Abstract :
Speech prosody is believed to carry much language-specific information that can be used for spoken language recognition (SLR). In the past, the use of prosodic features for SLR has been studied sporadically and the reported performances were considered unsatisfactory. In this paper, we exploit a wide range of prosodic attributes for large-scale SLR tasks. These attributes describe the multifaceted variations of F0, intensity and duration in different spoken languages. Prosodic attributes are modeled by the bag of n-grams approach with support vector machine (SVM) as in the conventional phonotactic SLR systems. Experimental results on OGI and NIST-LRE tasks showed that the use of proposed attributes gives significantly better SLR performance than those previously reported. The full feature set includes 87 prosodic attributes and redundancy among attributes may exist. Attributes are broken down into particular bigrams called bins. Four entropy-based feature selection metrics with different selection criteria are derived. Attributes can be selected by individual bins, or by attributes as batches of bins. It can also be done in a language-dependent or language-independent manner. By comparing different selection sizes and criteria, an optimal attribute subset comprising 5,000 bins is found by using a bin-level language-independent criterion. Feature selection reduces model size by 2.5 times and shortens the runtime by 6 times. The optimal subset of bins gives the lowest EER of 20.18% on NIST-LRE 2007 SLR task in a prosodic attribute model (PAM) system which exclusively modeled prosodic attributes. In a phonotactic-prosodic fusion SLR system, the detection cost, Cavg is 2.09%. The relative detection cost reduction is 23%.
Keywords :
feature extraction; speech recognition; support vector machines; F0 multifaceted variations; NIST-LRE 2007 SLR task; OGI tasks; PAM system; SVM; bin-level language-independent criterion; entropy-based feature selection metrics; individual bins; language-independent manner; language-specific information; large-scale SLR tasks; n-grams approach; optimal attribute subset; phonotactic-prosodic fusion SLR system; prosodic attribute model system; prosodic attributes; prosodic features; relative detection cost reduction; speech prosody; spoken language recognition; support vector machine; Language identification; mutual information; prosody;
fLanguage :
English
Journal_Title :
Audio, Speech, and Language Processing, IEEE Transactions on
Publisher :
ieee
ISSN :
1558-7916
Type :
jour
DOI :
10.1109/TASL.2013.2260157
Filename :
6508858
Link To Document :
بازگشت