A Hierarchical Automatic Language Identification System for Indian Languages Using Acoustic Features

Automatic spoken language identification (LID) is the task of identifying the language from a short utterance of the speech signal uttered by an unknown speaker. This paper describes a novel two level identification system for Indian languages using acoustic features. In the first level, the system identifies the family of the spoken language, and then it is fed to the second level which aims at identifying the particular language in the corresponding family. The proposed system has been modelled using Hidden Markov Model (HMM) and utilizes the acoustic features namely Mel frequency cepstral coefficients (MFCC) and Shifted delta cepstrum (SDC). A new database has been created for 11 Indian languages. The proposed system achieves a high accuracy of 62.36% for MFCC features and 71.2% for SDC features.