Introducing a FM based Feature to Hierarchical Language Identification

Abstract

Although relatively neglected in auditory analysis, phase information plays an important role in human auditory intelligibility. This paper investigates a Frequency Modulation (FM) based feature and its contribution to a Language Identification (LID) system, using a Hierarchical LID framework. FM components represent the phase information of a given signal in an AM-FM model. In this paper, we extract a FM-based feature using a technique which produces consistent and continuous FM components, and build a LID system on this feature with GMM based modeling. The performance is improved by combining this system with existing MFCC, Prosody based systems and a PRLM system. When compared to the baseline system without integrating a FM-based system, the proposed Hierarchical LID system shows improvements. Additionally, the proposed system outperforms the GMM fusion-based system integrating the same four primary systems, showing that the Hierarchical LID framework is more effective in integrating additional features.