Audio Retrieval using Hash-Index SearchTechnique

Abstract

An audio fingerprint is one of the generated content-based signature from original audio file that refers to an audio recording. Audio Fingerprinting technique is commonly used to monitor the audio independently without the need of meta-data. Different fingerprinting approaches are Pattern matching, Multimedia Information Retrieval and Cryptography. For browsing and identifying the audio content from large digital music audio data collection set is a major strand for research.The best solution for identifying the audio content is “Audio ID System” in which the specified audio is identified by passing a short query audio clip from a large set of audio data set. The popular audio fingerprinting schemes with a common audio fingerprinting framework with short query captured from microphone, are surveyed. The audio system originally developed by Haitsma and Kalker is most widely used and it proposes several modifications and improvements with to increase audio retrieval speed and storage requirements.