How Shazam worked pre-AI: spectrogram peaks hashed into a hashtable lookup
deedydas · x · 2026-10-06
Responding to a viral question about how Shazam identified songs 15 years ago without AI, deedy explains the core technique: take spectrograms of short clips from every song, extract peaks from the highest-amplitude points, and hash them with (timestamp, track ID) as the value — actual recognition is then just a hashtable lookup. He built this for a college CS project and recommends the original paper.
More from Fun
- Dev builds Crash Out, a 3D rage game where you beat up your problems, in 30 minutes with AI — Tegadesigns · 2026-10-06
- AI slop movies are now showing up on in-flight streaming as 'genuine' franchises — moyix · 2026-10-06
- Claude Opus 5.5 worked autonomously for 1h37m to flex its own capabilities — mcraddock · 2026-10-06
- Doomers are pouring big money into a sudden wave of high-quality doomer YouTube content — basedjensen · 2026-10-06
- A game where you beat up your problems, built in 30 minutes with prompts — Tegadesigns · 2026-10-06
- Claude Opus 5.5 lists the 20 jobs it will replace — according to itself — minchoi · 2026-10-06