contemporary with TunePrint https://www.mattababy.org/~belmonte/Tuneprint/ and at least one other. (Somehow TunePrint managed to get a record label to fill a fileserver with audio files and ship it back across country to use as training data - one of the stranger applications ever for AFS :-)
Such impressive engineering behind it. I remember using Shazam for the first time and thought it was an absolute game changer. I still use it through Siri to identify songs I hear out in the wild.
Didn't realise it existed all the way back to 2003, which makes it all the more impressive
So fundamentally just a ton of locality sensitive hashing, cleverly chosen to match the domain. Still wild that they shipped this in the flipphone era.
There's a python library called dejavu[0] that does similar hashing. It mostly works to make your own Shazam (assuming you can source the data to hash!)
Yup, agreed. Currently at 4 billion hashes and matching takes 30-120s. I haven't put effort into speeding it up yet because I'm using it for a trivia contest and we have a couple hours to figure out the clips.
HN search (in the page footer) uses the great service at https://hn.algolia.com, which will return those results, and more, indexing post titles, comments, and other categories for search.
Though I imagine he has a script for this use case though.
I worked at a startup way back when which using (I believe) a competing algorithm to match both images and audio. I really wish it had been Shazam... I might be rolling in it now...
That was... 2001ish?
(warning: too much alcohol in the system. Read with skepticism!)
Merlin (Bird ID) should rebrand to Shazam for Birds or something to that effect, becuase thats what it is. It always blows ppls minds, and they always say something to that effect about the name.
It runs locally so make sure you install and download over wifi (bird models for west coast about about 800mb last I checked.
It feels even more impressive to me because it's always used outside and picks up multiple birds easily. Our current record is 14, and we live near a busy road.
29 comments
[ 2.7 ms ] story [ 50.0 ms ] threadDidn't realise it existed all the way back to 2003, which makes it all the more impressive
There's a python library called dejavu[0] that does similar hashing. It mostly works to make your own Shazam (assuming you can source the data to hash!)
[0] https://github.com/worldveil/dejavu
https://github.com/AddictedCS/soundfingerprinting
How does Shazam work? (2022) - https://news.ycombinator.com/item?id=38531428 - Dec 2023 (154 comments)
An Industrial-Strength Audio Search Algorithm (2003) [pdf] - https://news.ycombinator.com/item?id=33299853 - Oct 2022 (1 comment)
Creating Shazam in Java (2010) - https://news.ycombinator.com/item?id=32530056 - Aug 2022 (36 comments)
Shazam turns 20 - https://news.ycombinator.com/item?id=32520593 - Aug 2022 (227 comments)
How Shazam Works (2015) - https://news.ycombinator.com/item?id=23806142 - July 2020 (7 comments)
Designing an audio adblocker - https://news.ycombinator.com/item?id=18855029 - Jan 2019 (186 comments)
Show HN: A radio/podcast adblocker featuring ML and Shazam-like fingerprinting - https://news.ycombinator.com/item?id=18459058 - Nov 2018 (2 comments)
Apple has completed its acquisition of Shazam - https://news.ycombinator.com/item?id=18066724 - Sept 2018 (316 comments)
Apple Buys Shazam to Boost Apple Music - https://news.ycombinator.com/item?id=15899065 - Dec 2017 (156 comments)
Apple is close to acquiring Shazam, sources say - https://news.ycombinator.com/item?id=15881896 - Dec 2017 (292 comments)
Show HN: Shazam-like acoustic fingerprinting of continuous audio streams - https://news.ycombinator.com/item?id=15809291 - Nov 2017 (76 comments)
How Shazam Works (2015) - https://news.ycombinator.com/item?id=15350729 - Sept 2017 (13 comments)
Tell HN: Shazam picks up song from my kitchen light - https://news.ycombinator.com/item?id=11593305 - April 2016 (2 comments)
How Shazam works - https://news.ycombinator.com/item?id=9870408 - July 2015 (48 comments)
Patent infringement claim re: “Creating Shazam in Java” blogpost (2010) - https://news.ycombinator.com/item?id=9594480 - May 2015 (18 comments)
The Shazam Effect (2014) - https://news.ycombinator.com/item?id=9593429 - May 2015 (37 comments)
The Shazam Effect - https://news.ycombinator.com/item?id=8634357 - Nov 2014 (34 comments)
Ask HN: Is there an audio search technology that finds exact and similar audio? - https://news.ycombinator.com/item?id=8420141 - Oct 2014 (3 comments)
Source code example of the Shazam algorithm - https://news.ycombinator.com/item?id=5724442 - May 2013 (16 comments)<...
Though I imagine he has a script for this use case though.
* "related. comments" https://hn.algolia.com/?dateRange=all&page=0&prefix=true&que...
* "related. comments dang" https://hn.algolia.com/?dateRange=all&page=0&prefix=true&que...
* "Related. comments dang news.ycombinator.com" https://hn.algolia.com/?dateRange=all&page=0&prefix=true&que...
That was... 2001ish?
(warning: too much alcohol in the system. Read with skepticism!)
I miss the dot com boom.
It runs locally so make sure you install and download over wifi (bird models for west coast about about 800mb last I checked.
https://merlin.allaboutbirds.org/
[1]: https://xkcd.com/1425/