JPR_V2_N1_RP4 Manogna Maddali C. Shoba Bindu Journal on Pattern Recognition 2350-112X 2 1 23 28 Automatic Language Identification (LID), Speech Rhythm, Mel Frequency Cepstral Coefficients, Phoneme Recognition, Language Model Automatic Language Identification is the task of identifying the Spoken Language, given utterance of speech. Many Communication Systems make use of this LID. Acoustic properties are used in many experiments, as it is easy to differentiate. Instead of using these features, prosodic properties can be used to identify the Language. The main idea is to explore the duration of neighboring syllable like units as a language discriminative feature. This paper proposes a LID which uses the rhythmic properties of Spoken Speech. Prosodic Features are extracted using Mel Frequency Cepstral Coefficients (MFCC). Based on the energy levels in the Signal, Phoneme Recognition is done to identify the syllable, like units. ANN is used to train the system and results are generated. The main focus of this paper is to improve the Recognition Accuracy. The error rate is reduced when compared with other systems. March - May 2015 Copyright © 2015 i-manager publications. All rights reserved. i-manager Publications http://www.imanagerpublications.com/Article.aspx?ArticleId=3373