Audio Fingerprinting Via Cell Phones 89
aruil writes: "MSNBC has a story reporting on yet another audio fingerprinting application. Next year, Royal Philips Electronics will begin selling licenses to allow users to identify songs using their cell phones. Similar technology has already been open-sourced in FreeAmp, which uses the Relatable engine."
Possible applications? (Score:1)
Re:Possible applications? (Score:1)
Cheating (Score:2)
Kind of hopeless... (Score:4, Interesting)
And what about the distortion this will cause in the audio? It's not like FM radio is great quality, but embedding some sort of watermark/fingerprint that only requires 3 seconds of playback has got to have some sort of negative impact on the sound.
Anyway, what the hell is up with all these trolls tonight? Time to start browsing at +2 now I guess.
you don't get it: (Score:2, Informative)
Re:you don't get it: (Score:1)
If it's the latter, then that'd be very interesting - they've essentially implemented 'grep' for audio!
It's "interesting" but I can't think of many uses of it apart from copyright enforcement.
I'd like to feed this system three seconds of "baby baby baby baby" from a generic pop song, and see how confused it gets.
Re:you don't get it: (Score:1)
nice idea... will probably return SONG BY BRITNEYSTEPSA-TEENSBRYANADAMSZONEMALFUNNNNNNNCTIO
definitely points toward non-watermarking:
All that?s required is to hold a mobile phone to a radio?s speaker for three seconds ? long enough to record a digital fingerprint ? when a song is playing.
Re:you don't get it: (Score:1)
For example, it can be used to determine whether or not songs are similar, and therefore be used to find songs similar to what you listen to a lot and would likely enjoy. Or to create good mixes on the fly.
It can be used for 'radio tivo' applications, editing ads out of broadcast radio. (because it knows what bit of the pre-recorded radio was ad, and what wasn't.) And of course, it's handy for automatic station changing.
Naturally, it's useful to be able to ID a song that's playing where you wouldn't otherwise know what it is. And a great tool for ID'ing mp3s and looking them up on a CDDB type database to fill the ID3 tags. (if for example, you hadn't done so when you ripped it)
I was working on some mp3 projects for a while -- we were definately hoping to make use of this kind of stuff.
Re:you don't get it: (Score:1)
Re:Kind of hopeless... (Score:2)
It was Sony. It was basically a clock with a USB interface. When you heard a song you wanted to identify, you pressed a button, and it stored a timestamp. When you got home, you plugged it into the USB port, and the software read the timestamps, and then reported what was playing on the participating radio stations in your area at those times.
They had quite a few more than two radio stations.
oh great (Score:1)
please. is it really that hard to ask ya friend (you know
yet another technological instrument that if implemented properly along with many other features could contrubute to a useful device, but instead will probably be marketed as a gimmick (just like that blue led "flashlight" you have at the bottom of your desk drawer, don't deny it) and eventually be dismissed as useless.
btw this wasn't meant as a flame. go ahead and -1 it but basically waht i'm trying to say is that these devices have uses which could make them successful, who wouldn't want to know in the middle of a tv show or movie or music vid what song they're listening to. i just get annoyed at the poor implementations and over hype of such ideas
and just disregard this if it makes no sense
-john
Nothing to do with Charlie's Angels then (Score:2)
Re:Nothing to do with Charlie's Angels then (Score:1)
But until they do, we're safe from THEM spying and tracking us through the phone.
Oh dear, I hope those Angels do something to avert this looming crisis.
~Duane
"another" link (Bitzi) (Score:4, Informative)
Question (Score:2)
Re:Question about Bitzi (Score:1)
So while there are some similarities, and if you could get perfect bit-for-bit CD rips then Bitzi would duplicate a lot of what FreeDB does, there's no pressing need for a combined offering. If there was, it wouldn't be too hard for either project to use whatever data it needed from the other, within the free licenses.
(FYI: I am the CTO of Bitzi.)
Re:Question about Bitzi (Score:2)
For music files, this would of course be FreeDB. For movies, a good choice would be IMDB etc.
For instance, if I look up one of my Nightwish songs, Bitzi gives me the following information:
http://bitzi.com/lookup/TTGZBRZLZ2HLXDHSQYBTEJD33
the data from FreeDB is more accurate, giving the album the song belongs to, the playtime etc.
http://www.freedb.org/freedb_search_fmt.php?cat=r
Re:Question about Bitzi (Score:1)
- You need a discid (or the track offsets used to calculate discid), and generally someone with a file won't have access to the discid, so there really isn't any way to look up FreeDB information given just a file, which is what Bitzi has to work with.
- FreeDB is GPL, Bitzi is dmoz-like (OpenBits).
Those caveats aside, in the longer term I do hope to see collaboration and cross-pollination among all free catalog projects.Any 3 seconds!? (Score:3, Interesting)
An even better solution (Score:4, Interesting)
I have tried it and can confirm it works really well.
Story from newscientist.com here [google.com]. (cache)
Also a article from GEMENI here [www.ntnu.no].
Re:An even better solution (Score:2)
Offtopic: * 2001-11-30 12:33:57 Mobile Phone System Identifies Music (science,news) (rejected) -- This was originally a New Scientist article indeed. All my submitted stories so far have been rejected, only to be accepted weeks later in a worse write-up by someone else. I will submit no more stories - it seems a huge waste of effort to me. No thanks.
Re:An even better solution (Score:1)
Re:An even better solution (Score:1)
Not really useful.. (Score:1)
What would be more useful is where you could hum a song into the phone, and it could tell you what it was. I personally need something like this as i've got this song in my head (with no lyrics so you can't use Google [google.com] to find it) that is driving me nuts as I try looking for it. The ability to hum it in and give it further parameters to search for would be good.
Re:Not really useful.. (Score:1)
God, I need more coffee.. (Score:2, Insightful)
And, correct me if I am wrong but this kinda says "digital watermark":
"The fingerprint might contain small mistakes. The technology is so robust that it can handle that," said Jaap Haitsma, a Philips research scientist.
Haven't we gone thru this already?
Seriously. The only thing missing was an SMDI challenge and the RIAA. Even though Microsoft is involved in this, I'm quite sure the RIAA will (pardon the pun) chime in Very Soon Now(TM).
Ok, quit possibly I am missing the point, but read this:
As well, a legitimate online music services running on the Napster model could use the technology to stop copyright-protected material from being shared.
Legitimate, Napster and stop sharing all in the same sentence?
Eh? The whole point of Napster was to share (leave out the legit or not) songs.
{Pitr voice}
Someone please to be explainink this to me.
{/end voice}
Moose.
.
The real test is: (Score:2, Funny)
Re:The real test is: (Score:3, Funny)
I wonder if it can distinguish between... (Score:1)
Probably difficult to do (Score:1)
Remember that the way digital cell phones work is that they analyze the sound input, and send it not as audio data, but as coefficients to a human-voice synthesis DSP to save bandwidth. Digital cell phones are really only good for transmitting and recieving human voices, and are really really bad at music.
So it is rather suprising to me that such as technology is feasible.
Re:Probably difficult to do (Score:2)
Err, what?
You're talking about GSM encoding [bdti.com]?
"The quality of the algorithm is good enough for reliable speaker recognition; even music often survives transcoding in recognizable form (given the bandwidth limitations of 8 kHz sampling rate)."
What's this about human voice synthesis DSP? Sounds a bit black-helicopters-faked-the-moon-landing to me. (or else I'm totally out of it - it happens! my cellphone here's still analog)
Re:Probably difficult to do (Score:1)
Check it out [selbyventures.com]. Or do a google search.
I've seen this.... (Score:2, Informative)
1) No tampering is done to the audio - ie there is no watermark, it is "just" signal processing.
2) The system I saw could take any 3 or 4 seconds, so that means that a fingerprint was calculated over the whole song. This means they must have some clever algorithms to make sure that the hash is calculated using the same time slices (or something...)
3) The song has to be in the database. So that means that the fingerprint has already been calculated, and probably had metadata assigned to it either by hand or using mp3 id3 tags (this is a guess). The fingerprint size is about 16KB per song, which seems pretty reasonable.
4) The technique only works on a per-recording basis, so even the same performer doing a slightly different version or another recording won't match if that recording was not already fingerprinted.
5) The version I saw was standard PC software, using audio input through the microphone.
My suspicion is that this technology is more likely to be of value to copyright holders looking to automatically identify violations (eg public airings, radio stations not paying royalties) than it will be useful to joe sixpack (or even people like us...)
Show me the money (Score:2, Interesting)
As a musician, I value authenticity and would love to have an app that would prevent my brain from tricking me into thinking I had composed a remembered melody. Also, many people would love to know what that song stuck in their head is. However, is this enough consumer interest to sustain such a product? Furthermore, is there a chance that copyright lawyers will get out of control with this kind of power?
Alternative uses for this technology? (Score:3, Insightful)
Gone are the methods of avoiding detection [slashdot.org] used to date.
Even if this detection has no way to discern between the original and a cover of the song, I can see the RIAA and major labels nailing a bunch of people, and using this system as proof.