Title :
The Design of Backend Classifiers in PPRLM System for Language Identification
Author :
Suo, Hongbin ; Li, Ming ; Liu, Tantan ; Lu, Ping ; Yan, Yonghong
Author_Institution :
Chinese Acad. of Sci., Beijing
Abstract :
The design approach for classifying the backend features of the PPRLM (Parallel Phone Recognition and Language Modeling) system is demonstrated in this paper. A variety of features and their combinations extracted by language dependent recognizers were evaluated based on the National Institute of Standards and Technology (NIST) Language Recognition Evaluation (LRE) 2003 corpus. Three well-known classifiers: Gaussian Mixture Model (GMM), Support Vector Machine (SVM), and feed forward neural network (NN) are proposed to compartmentalize these high level features which are generated by n-gram language model scoring and one pass decoding based on acoustic model in PPRLM system. Finally, the log-likelihood radio (LLR) normalization is applied to backend processing to the target language scores and the performance of language recognition is enhanced.
Keywords :
Gaussian processes; feedforward neural nets; natural language processing; pattern classification; speech recognition; support vector machines; Gaussian mixture model; PPRLM system; acoustic model; backend classifiers; backend features; feedforward neural network; language identification; language modeling system; log-likelihood radio normalization; n-gram language model scoring; one pass decoding; parallel phone recognition; support vector machine; Decoding; Hidden Markov models; Lattices; Mel frequency cepstral coefficient; NIST; Natural languages; Neural networks; Speech; Support vector machine classification; Support vector machines;
Conference_Titel :
Natural Computation, 2007. ICNC 2007. Third International Conference on
Conference_Location :
Haikou
Print_ISBN :
978-0-7695-2875-5
DOI :
10.1109/ICNC.2007.719
