A Language Identification algorithm based on segmental feature and automatic tokenization
Bingxi Wang · Signal Processing · 2008
we present a new framework for language identification using acoustic and phonotactics information of specch.First,an automatic speech segmentation algorithm is performed in the preprocessing stage,then at the feature stage the segmental shift delta ceps- turm feature which carry long-term information is introduced,at the model stage a muhigram language model is developed based on the u- sing of traditional GMM for speech tokenization.A multi-class support vector machine is used for the backend classification.Experiment results demonstrate that the new system yields good performance in the language identification task of five languages in the OGI- TS database.