The Design of Backend Classifiers in PPRLM System for Language Identification
- Resource Type
- Conference
- Authors
- Suo, Hongbin; Li, Ming; Liu, Tantan; Lu, Ping; Yan, YongHong
- Source
- Third International Conference on Natural Computation (ICNC 2007) Natural Computation, 2007. ICNC 2007. Third International Conference on. 1:678-682 Aug, 2007
- Subject
- Computing and Processing
Natural languages
Neural networks
Support vector machines
Support vector machine classification
Hidden Markov models
NIST
Decoding
Lattices
Speech
Mel frequency cepstral coefficient
- Language
- ISSN
- 2157-9555
2157-9563
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 feedforward 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.