Computer Science & Engineering: An International Journal (CSEIJ), Vol.1, No.3, August 2011 DOI : 10.5121/cseij.2011.1302 13         Sandeep Chaware 1 , Srikantha Rao 2 1 Research Scholar, MPSTME, NMIMS University, Mumbai, INDIA {smchaware@gmail.com} 2 PhD Guide, MPSTME, NMIMS University, Mumbai, INDIA {dr_s_rao@hotmail.com} ABSTRACT Phonetic matching plays an important role in multilingual information retrieval, where data is manipulated in multiple languages and user need information in their native language which may be different from the language where data has been maintained. In such an environment, we need a system which matches the strings phonetically in any case. Once strings match, we can retrieve the information irrespective of languages. In this paper, we proposed an approach which matches the strings either in Hindi or Marathi or in cross-language in order to retrieve information. We compared our proposed method with soundex and Q-gram methods. We found better results as compared to these approaches. KEYWORDS Soundex, Q-gram, Edit distance, Indic-phonetic, phonetic matching. 1.INTRODUCTION Phonetic matching is needed when many diversified people come together. They either speak with different pronunciation styles or write many languages in various writing styles, but their meaning is same. It deals with identified the similarity of two or more strings by pronunciation, regardless of their actual spelling. A typical example is Just-Dial service in Mumbai, where a telephone operator is given a name for finding out the information for the same. The operator guesses for the possible spelling of it, and then searches from the database (or spelling may be provided which may be incorrect). Phonetic matching plays an important role in information retrieval in multilingual environment. Information retrieval means searching the data in a database for retrieval. For this indexing and ranking will be used. Information retrieval needs an exact match for a given string. Phonetic matching can be defined as a process of identifying a set of strings those is most likely to be similar in sound to a given keyword [1]. The strings can be spelled using different writing styles, but they can be matched phonetically. All the strings represent the same keyword, only way of writing is different. Since in rural areas, the word may be spelled or pronounce either wrongly or differently. We can retrieve the data using phonetic matching. There is no need of exact string matches.