Finally someone did this. I've got a million songs in my head that I'm humming not knowing what songs these are. And I was dreaming of being able to simply hum a melody to something shazam-like and get a result.
I’m fairly sure SoundHound has had this feature since the early 2010s. Haven’t heard of the app since, but apparently their site is still up. I think Shazam ended up winning the music ID race as I remember having both apps.
The long-available one is similar to how siri / shazam / etc work - it only detects the actual song. I forget how the audio fingerprinting works (probably varies by system anyway), but they tend to be pretty picky and very sensitive to small timing or frequency changes on "interesting" audio points. E.g. even quite-true-to-the-original covers often fail to find matches for me.
I was confused too at first. Installed the app and pressed the microphone icon, but didn’t notice the button. Was it even there?
But then after I’d uninstalled the app I went back and reread the article and saw it say to press microphone and then button for search a song, reinstalled app and then I saw the button there.
Still don’t know if it was there or not the first time around. Maybe I just didn’t see it? Either way, it’s there now. Using iOS btw.
I was curious to see how it would fare because for example when I’ve tried to hum into Shazam or SoundHound in the past they’ve never come close to finding what I was looking for.
But I read in the article that Google is using machine learning and that they have actually trained their hum to search on recording of humming so I got my hopes up.
So in the Google search app I hummed a part of the melody for the song What is Love by Haddaway and... it recognized it! I’m impressed!
Just tried it out on my throwaway Android. Wow, this actually works really well!
As I write this from my iPhone, this might singlehandedly be the reason why I switch to a Pixel instead of another iPhone this fall. I was always disappointed that even after acquiring Shazam, Siri could never seem to correctly guess what song was playing unless I had a perfect recording.
Anytime I go to a live concert venue, or even a club, I never can get a recognizable song from my phone. Live music I could maybe sort of understand, but the club part failing was always weird to me, because besides a little bit of distortion, the song being played is coming directly out of a speaker. It shouldn’t be that hard right?
Nice! It showed up after I reinstalled it. If I end up wanting to do so, is there a way to potentially replace Siri with Google somehow in the settings?
This is probably cross platform; But what is not cross platform is the "Now Playing" feature of Pixels, that enables ambient songs matching in the background (without the use of internet, you can confirm with airplane mode). It keeps a list of songs that it identifies as well...
Also the recorder app, which is the bomb (transcribing without internet, searchable, editing (cuts and joins audio) and creating a video with transcription). Cool stuff
I just tried this with a melody I've had stuck in my head for days - no results.
Then I tried "Happy Birthday" and got three results:
"Las Mananitas" by Canticos
"Iyi Ki Dogdun Melissa", by Eser Ulun
"Iyi Ki Dogdun Zarife", by Eser Ulun
I'm no Pavarotti, but I can sing on pitch and have played the violin for 40 years.
EDIT: Heh, "Iyi Ki Dogdun" is Turkish for Happy Birthday, and the links would have taken me to YouTube videos of the song sung in Turkish, then English. But why not to videos in English? YouTube has some, and I'm an Anglophone user in the USA.
That's probably it. I'm not a great singer, and I wanted to see if it could recognize my attempt at a challenging melody. It got "Everybody Wants You" by Billy Squier, first try.
I think that, as of this moment, the tool does not take the user's current region into account. I know two songs that are very similar[0][1], but from vastly different regions, and I could easily get them both detected by this tool just by humming slightly differently.
My Turkish isn't great but, iyi ki dogdun translates to "good thing you were born" which always amused me. Happy birthday is more like "dogum gunun kutlu olsun" (something like, may your day of birth be celebrated). It's always fun to see how language gets worked with to fit a certain melody.
Very unlikely that they are considering the actual sung or hummed pitch as very few people, including professional musicians, would start singing at the correct pitch without accompaniment.
Most likely they are mapping the interval between the sung notes and using that as part of the ‘melodic fingerprint’ for matching.
I'm not sure how you were doing it, but when I think of "hum", I think of making a noise with my mouth closed. I found opening my mouth and making a tone worked much better.
I'm not sure how many people think of hum the same way. I've noticed lately some words being used slightly differently than I am used to (the one coming to mind right now is "giggle" in a story that in context I would interpret as meaning "chuckle"), and at this point it's happening enough that I'm not sure if there's a shift in perception of these words or if I just always interpreted them more narrowly than they were intended.
Well, there was this (now-deleted) song-identification-request posted on Stack Exchange a few months ago: https://i.stack.imgur.com/31A2G.png
> I have the tune in my head of a metal song. but I can't figure out. It's goes like on guitar ha ha ha. ha ha ha haaaaaaaaaaaaaaaaa. ha ha ha ha haaaaaaaaaaaaaaaaaaaaaaaaa.
Hold your finger on the image in chrome and in the pop-up menu there's 'search with google lens'. On https://www.google.com/imghp?hl=EN if you request a desktop site there's an upload capability as well...
But you are aware that the vast majority of users would be on mobile, right?
I mean I recognize that Translate on images in the browser - especially if combined with Youtube and Image Search - would be incredibly powerful, but it just wouldn't be as much a thing on desktop.
I'm pretty sure (don't quote me on this) that there's a bit of processing done on the device (character recognition / isolation) before sending it off to Translate as well; not sure how well that would port to a browser. Should work just fine with wasm though.
Only works for English songs. I searched for a Pakistani song as famous as national anthem ("dil dil Pakistan"). It couldn't find it.
I was thinking it learns the tune of song and matches with that so language should not matter.
It worked for "Desert Rose" though.
Edit: Also worked for an Indian song.
Also worked for few other recent famous Pakistani songs. I guess the first song that I searched is probably not listened on YouTube as much as its known by heart.
It could not search for national anthem itself for the reason.
I think it's talking about the interface language, not the actual content. I'm pretty much sure it connects to the same endpoints for the actual hum and data, so there should be no difference.
I tried the Portuguese anthem three times, with lyrics. I got a Japanese anime song, a French lullaby about a baby bear and "All I want for Christmas".
This has consumed my morning. I've been humming out all of random tunes of my childhood from folk music to pop that I never knew the name of. It works.
I dowloaded the Google app, said “what’s this song,” and it just searched Google for the words “what’s this song” instead of listening for humming. Am I doing something wrong?
Edit: After tapping the microphone icon, I have to tap the “search a song” button instead of saying “what’s this song”
I am a non-native English speaker, and I have been trying songs from different countries. I did notice that English songs have a better match than songs from other regions and languages[0]. I wonder if their training dataset has "overfitted" to such music, or is such music inherently represented by some underlying features that are better distinguished than others.
[0]: E.g. English ("My Heart will Go On" and "Skyfall") fit with 78% and 85% respectively, while Japanese ("Tonari no Totoro") and Hindi ("Tum Hi Ho") fit with 42% and 48% respectively
It depends on how good you can hum, I tried couple of english songs (Fix You, Ophelia, etc) it was around 18-20%, "Kya Hua tera wada" a Hindi song was matched with 48% I believe
> This feature is currently available in English on iOS, and in more than 20 languages on Android. And we hope to expand this to more languages in the future.
I'm a very musically challenged person, people usually don't recognize when I'm humming a song they like for them, and it used to really infuriate me.
So, I bought SoundHound 8+ years ago in a Google Market promotion offering several apps for pennies (10c, I guess?). Tried it without much hope and damn it, it worked well. Sometimes it goofed, but truth be told, it may be my problem.
Also, it had the ability to identify covers in a crowded bar, or non-playback live versions. Shazam, which was very popular at the time, admittedly couldn't do any of that - in their FAQ (which I could not find right now) they even told that if Shazam recognize a live version, it must be either a playback or a player with microsecond precision repeatability.
There's a video of a streamer saying 'hey google, play the mexican doot doot song' and it plays, and this reminds me of that. Unfortunately I can't find the video because I think google strips out 'hey google' even when you're specifically searching for the phrase 'hey google'.
'The song is best known under the alternative title "Sukiyaki". In Japan it refers to a Japanese hot-pot dish with cooked beef, the word sukiyaki does not appear in the song's lyrics, nor does it have any connection to them'
"Ei wrote the lyrics while walking home from a Japanese student demonstration protesting against a continued US military presence in the country, expressing his frustration at the failed efforts."
"An instrumental version of the song was played by NASA over the radio for the Gemini VII astronauts as mood music, thereby becoming one of the first pieces of music sent to humans in space."
Ha! From the get go I remembered I heard this song in a Studio Ghibli movie, then a google search quickly told that it was on From Up On Puppy Hill :-p. I love the Internet.
That wouldn't answer the question. Searching a song that you remember from the past is nothing like listening to a song on YouTube and then immediately trying to sing it back to Google.
Just once, humming (not particularly well), not singing.
The song in question is sung with a very clear voice, with minimal instrumental backing. That may suggest the limiting factor is Google's ability to parse songs, rather than users' ability to hum them.
Tried it with soundhound [0] (was called midomi when I used it as a flash app many years ago) just for giggles and it found a different version of the same song first try as well.
230 comments
[ 2.7 ms ] story [ 247 ms ] threadedit: works for me now. After a few minutes the button just started showing up
But then after I’d uninstalled the app I went back and reread the article and saw it say to press microphone and then button for search a song, reinstalled app and then I saw the button there.
Still don’t know if it was there or not the first time around. Maybe I just didn’t see it? Either way, it’s there now. Using iOS btw.
I was curious to see how it would fare because for example when I’ve tried to hum into Shazam or SoundHound in the past they’ve never come close to finding what I was looking for.
But I read in the article that Google is using machine learning and that they have actually trained their hum to search on recording of humming so I got my hopes up.
So in the Google search app I hummed a part of the melody for the song What is Love by Haddaway and... it recognized it! I’m impressed!
As I write this from my iPhone, this might singlehandedly be the reason why I switch to a Pixel instead of another iPhone this fall. I was always disappointed that even after acquiring Shazam, Siri could never seem to correctly guess what song was playing unless I had a perfect recording.
Anytime I go to a live concert venue, or even a club, I never can get a recognizable song from my phone. Live music I could maybe sort of understand, but the club part failing was always weird to me, because besides a little bit of distortion, the song being played is coming directly out of a speaker. It shouldn’t be that hard right?
edit: now the button does show up. Tried humming "Peter and the wolf" and it failed.
The button is there for me, and hum to search works.
Screenshot: https://snipboard.io/ITZN9A.jpg
When I first installed the app after reading the article, to test it out, I couldn’t find it even when I pressed the microphone symbol.
But after rereading the article I installed it again and when I went and tapped the microphone I saw the Search a song button.
Immediately after updating, there was no button. Maybe something changed on their end or something needed to sync in my phone.
It's almost spookily accurate
Then I tried "Happy Birthday" and got three results:
"Las Mananitas" by Canticos
"Iyi Ki Dogdun Melissa", by Eser Ulun
"Iyi Ki Dogdun Zarife", by Eser Ulun
I'm no Pavarotti, but I can sing on pitch and have played the violin for 40 years.
EDIT: Heh, "Iyi Ki Dogdun" is Turkish for Happy Birthday, and the links would have taken me to YouTube videos of the song sung in Turkish, then English. But why not to videos in English? YouTube has some, and I'm an Anglophone user in the USA.
I'm pretty sure it's an instrument line, not vocal.
https://www.youtube.com/watch?v=pXrjMaVoTy0
[0] https://youtu.be/E8gmARGvPlI?t=17
[1] https://youtu.be/mSu5cz2GFts?t=43
Also, why the hell do I need an app for this? Is it actually running a local model? Because my guess is that it's just hitting an API.
There's no way it would do much locally, but maybe they just wanted to make sure the audio passed to the API has a certain sample rate and encoding?
Most likely they are mapping the interval between the sung notes and using that as part of the ‘melodic fingerprint’ for matching.
https://en.wikipedia.org/wiki/Happy_Birthday_to_You#Copyrigh...
I'm not sure how many people think of hum the same way. I've noticed lately some words being used slightly differently than I am used to (the one coming to mind right now is "giggle" in a story that in context I would interpret as meaning "chuckle"), and at this point it's happening enough that I'm not sure if there's a shift in perception of these words or if I just always interpreted them more narrowly than they were intended.
I tried using my mouth open and didn't get significantly different results, though.
"song that goes meow meow meow meow meow meow", can't find it at the moment for a timestamp. Wonder how many real queries of that actually happen.
> I have the tune in my head of a metal song. but I can't figure out. It's goes like on guitar ha ha ha. ha ha ha haaaaaaaaaaaaaaaaa. ha ha ha ha haaaaaaaaaaaaaaaaaaaaaaaaa.
Reminds me of Google Translate on photos/images, which has been available for years on mobile but never on web.
I hope this doesn't become a trend.
I mean I recognize that Translate on images in the browser - especially if combined with Youtube and Image Search - would be incredibly powerful, but it just wouldn't be as much a thing on desktop.
I'm pretty sure (don't quote me on this) that there's a bit of processing done on the device (character recognition / isolation) before sending it off to Translate as well; not sure how well that would port to a browser. Should work just fine with wasm though.
I was thinking it learns the tune of song and matches with that so language should not matter.
It worked for "Desert Rose" though.
Edit: Also worked for an Indian song.
Also worked for few other recent famous Pakistani songs. I guess the first song that I searched is probably not listened on YouTube as much as its known by heart.
It could not search for national anthem itself for the reason.
I was rather whelmed when I saw it could just find songs that were playing right now.
Edit: After tapping the microphone icon, I have to tap the “search a song” button instead of saying “what’s this song”
I am a non-native English speaker, and I have been trying songs from different countries. I did notice that English songs have a better match than songs from other regions and languages[0]. I wonder if their training dataset has "overfitted" to such music, or is such music inherently represented by some underlying features that are better distinguished than others.
[0]: E.g. English ("My Heart will Go On" and "Skyfall") fit with 78% and 85% respectively, while Japanese ("Tonari no Totoro") and Hindi ("Tum Hi Ho") fit with 42% and 48% respectively
What? Humming is not different across dialects.
So, I bought SoundHound 8+ years ago in a Google Market promotion offering several apps for pennies (10c, I guess?). Tried it without much hope and damn it, it worked well. Sometimes it goofed, but truth be told, it may be my problem.
Also, it had the ability to identify covers in a crowded bar, or non-playback live versions. Shazam, which was very popular at the time, admittedly couldn't do any of that - in their FAQ (which I could not find right now) they even told that if Shazam recognize a live version, it must be either a playback or a player with microsecond precision repeatability.
1) A "I'm finished humming" button
2) A way to tell Google what song I just hummed when it guessed wrong
It failed for me on "Sofia" and "Peter and the Wolf" -- maybe this only works for recently popular songs?
[1] https://www.youtube.com/watch?v=rbTsG9jrJsU
'The song is best known under the alternative title "Sukiyaki". In Japan it refers to a Japanese hot-pot dish with cooked beef, the word sukiyaki does not appear in the song's lyrics, nor does it have any connection to them'
"An instrumental version of the song was played by NASA over the radio for the Gemini VII astronauts as mood music, thereby becoming one of the first pieces of music sent to humans in space."
https://duckduckgo.com/?q=Sukiyaki+studio+ghibli&t=brave&ia=...
[0]: https://www.youtube.com/watch?v=ueVjrc7YYoE
[1]: https://www.youtube.com/watch?v=xqFkUNqBwMw
https://youtu.be/zk4Y7SbTQK8?t=164
Warning: potentially NSFW - language (for those still in offices)
The song in question is sung with a very clear voice, with minimal instrumental backing. That may suggest the limiting factor is Google's ability to parse songs, rather than users' ability to hum them.
https://youtu.be/-0mlFNmj-vU
Aha, so that's where I had heard it before!
[0] https://play.google.com/store/apps/details?id=com.melodis.mi...
Whistle and look up so you can't see these tears..
It managed to be a #1 hit in the US even!
1. https://www.youtube.com/watch?v=5nZueSZRJrA