YapHash | perceptual fingerprint for audio identification purposes

YapHash is a C library. YapHash has no bugs, it has no vulnerabilities and it has low support. You can download it from GitHub.

YapHash is a perceptual fingerprint for audio identification purposes. YapHash is part of the [VIAT Project] and therefore developed for detecting telephone-spam. Although it’s been optimized for speech content, it could also be used for other audio data. Standard cryptographic hash functions have the property that minimal alterations of input data significantly change the resulting hash value. Robust audio hashes in contrast produce identical or nearby hash values for similar input data. In particular, the audio hashes should be invariant to (certain) content degradations and hence permit a perceptual audio comparison and an efficient identification of a specific recording. Different recordings with similar content, e.g. identical words or phrases, or from the same speaker are not identified.