New Features for Language Identification Using Gmm

Automatic Language Identification (LID) is the process of identifying the language spoken within an utterance. The challenge that this task presents is that no prior information is available indicating the content of the utterance or the identity of the language. Most of the existing LID systems are based on MFCC feature vectors. This paper introduces the use of new feature extraction approach for LID task. For this, an approach is proposed to derive a new type of feature vectors from speech signal alone. The feature extraction method is based on the frequency of occurrence of phonemes is different for different languages. The variations in frequency of occurrence of phonemes are effectively captured using Gaussians. These variations are captures in the form of probability vectors using Gaussians. This approach outperformed the existing conventional MFCC feature vector based LID systems.