Hybrid query by humming and metadata search system (HQMS)

Abstract

Query by humming (QbH) is a technique that is used for audio content retrieval. Many QbH systems are based on a feature of humming comparison to audio files, which can be further improved by accompanying other approaches along with humming. In our study, we propose a Hybrid approach of QbH and Metadata search system as audio files retrieval. The proposed framework is based on the Pipe and Filter architecture that provides a serial structure with two filters in order to efficiently retrieve relevant files. Content Based searching works more swiftly when applied on a small collection of files and by using this quality our framework first filter files by audio file retrieval mechanism which will decrease the collection count to the most relevant files that would be further sieved by a second filter QbH. We find our research to be beneficial to the community, as it works on defining a new idea for audio file retrieval, made hybrid in order to achieve high precision and recall efficiently.