System and method for audio media recognition

Abstract

Automatic recognition of sample media content is provided, A spectrogram is generated for successive time slices of audio signal. One or more sample hash vectors are generated for a time slice by calculating ratios of magnitudes of respective frequency bins from a column for the time slice. In a primary evaluation stage an exact match of bits of the sample hash vector is performed to entries in a look-up table to identify a group of one or more reference hash vectors. In a secondary evaluation stage a degree of similarity between the sample hash vector and each of the group of reference hash vectors is performed to identify any reference hash vectors that are candidates for matching the sample media content, each reference hash vector representing a time slice of reference media content.

Description

technical field [0001] The present invention relates to audio recognition systems and methods for automatic recognition of audio media content. Background technique [0002] Various audio recognition systems and methods are known for processing incoming audio streams ("programs") and searching internal databases of music and sound effects ("tracks") to identify those tracks used within the program. [0003] In the real world, music is often the only layer in a program's audio layers. One of the challenges for audio recognition is to recognize the identity of the music even in the context of other audio layers such as sound effects, voice-overs, ambience, etc. that are present at the same time. Other distortions include equalization (adjusting the relative amounts of tremble and bass in a track) and changing tempo and / or pitch. [0004] Some audio recognition techniques are based on directly performing a neighbor search on the computed hash values ​​using standard algorithm...

AI Technical Summary

Problems solved by technology

Such standard algorithms do not perform very efficiently when the space being searched has a large number of dimensions

Images