This paper is concerned with designing speaker recognition systems in Indian languages for tape recorded speech and improving their performance with emphasis on system features. First the baseline ASR system using LP-based features (such as LPC and LPCC) and filter bank based features (such as MFCC) with polynomial classifiers of 2nd or 3rd approximation is built for speaker modeling. A relative comparison of experiments will perform on speaker identification for monolingual, cross-lingual and multilingual modes. Employing HMM and rapid search algorithm can do the multilingual speech recognition. In this paper the concentration is made on matching and searching words in Indian Languages. The proposed system is an efficient method to achieve the above goal.