Speech Retrieval using STD

Abstract

This paper given a brief survey on Speech retrieval techniques. In each and every technique discuss the advantages and disadvantages. The methods which are discussed in this paper are designed for low-useful resource occasions where confined or no in-domain coaching fabric is available and accurate word-centered speech consciousness potential is unavailable. Using these techniques, we demonstrate that it is indeed feasible to perform spoken term detection in low resource scenarios. Moreover, these show that efficient and practical STD systems could be developed which search through several hours of spoken data in real time. Spoken Term Detection (STD) is the task of detecting all occurrences of a query from spoken data. In this thesis, two types of STD techniques are explored. In the ?rst part, a query-by-example STD approach is presented for language independent search. In the second part, a text-based STD technique.