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.
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.
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.
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.
'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."
I recently had an epic earworm that involved lots of old school manual searching, which I'm kind of proud of.
For about two weeks I had this beautiful haunting melody stuck in my head. It would just turn on at certain times in the day and I'd find myself humming it. I have around 3500 CDs, mostly jazz but boatloads of classical stuff too. For days I rifled through bins of CDs (which is something I love doing) looking for the source. No dice.
Finally, a breakthrough: One day the song was playing in my head and I noticed the timbre of the instrument was a clarinet. And it was kind of raspy, which was weird, because the melody seemed more classical and classical clarinetists have super clean tone. I immediately knew to start looking for Don Byron albums, because he probably makes up 90% of my clarinet jazz albums. Sure enough, after a couple hours I found it. The last tune off the "Tuskeegee Experiments" album is a Schumann (!) piece called Auf einer Burg:
SoundHound came out with this feature in their iPhone app in 2008. It worked well in my experience. It’s amazing how quick we are to go ooo ahhh when big tech replicates what is already common place in little tech or academia.
I remember that, and I remember playing a game with my girlfriend at the time where we tried to get it to recognize any song we hummed. We had an in-joke where Smooth Operator was literally the only song we could get it to recognize.
This isn't just "big tech replicating a commonplace feature", it's big tech implementing it at all where little tech could not.
This is a common fetishization on HN, but HNers forget that execution is all that really matters. Little tech demos do not. Though we on HN act like tech demos are the hardest part.
> This isn't just "big tech replicating a commonplace feature", it's big tech implementing it at all where little tech could not.
Well I guess our experiences were quite different then. I was able to get SoundHound to recognize the vast majority of the tunes I hummed for it back in 2008/2009. And I used it a lot. I did only choose popular songs though. It's not surprising IMHO that a company 12 years later with much greater resources could extend recognition to a much larger variety of songs. So I wouldn't call it "little tech could not."
I think you are underestimating how popular Soundhound was (or overestimating how popular Google's version is). I bought my first smartphone just because I was blown away by Soundhound app. I was going to upgrade a year later but apps like SoundHound sealed the deal for me
My wife and I had a real wow moment with Shazam after we’d taken a trip to Germany and she’d heard some music played on a carousel at a park. She had a video of the carousel running and we played it to Shazam. In about 20 Seconds we were listen to a very similar recording of “Sie will nicht blumen und nicht schokolade” (She doesn’t want flowers or chocolate). It was a really awesome moment of technology working for us.
Wow, nice find! I'm glad I scrolled through the YouTube comments a bit to see this note on the background of the recording in wartime Berlin:
"Recorded in Berlin, June 17, 1941. This was based on an old Yiddish song 'Yossel, Yossel' (by Nellie Casman) which Sammy Cahn and Saul Chaplin later retitled 'Joseph, Joseph.' Wonder if the censors realized this."
I seem to remember that they even had an option to play back recordings of other users who hummed the same song you were humming. Of course it was a privacy minefield, so that feature was discontinued pretty quickly. But it was hilarious while it lasted, hearing e.g. a Japanese granny croon Madonna.
I remember that feature. Out of my, like 20 to 30 tries, it literally worked only once. I told about that feature to my friends too but they said that it wasn't working either.
So it was really not working at an acceptable level, or both me and my friends are terrible hummers.
I worked there from 2012 for 5 years. The query by humming was pretty amazing to me which is why I joined. And I'm pretty terrible at humming... Unfortunately though the database wasn't as extensive as the direct music match database. Perhaps you were trying songs that weren't included?
Fun anecdote: I witnessed one user sing a song into SH so pitch perfect that (from the results) it had made a direct music match!
We often heard that Google were attempting to replicate this technology. They even hired key employees involved in this part of the app. Still we maintained that particular technical moat for 12 years!
That was my first thought too. SoundHound worked 90% of the time for me, very impressive for the day IMO. Too bad it was fairly short-lived - I think they removed that functionality within a year or two. It's nice to have the ability to search like this again.
Recently getting on a tirade about how utterly pointless the comment "Linux had this first!" "Android had this first!" "Lisp had this first!" is. It's just as bad when it's "iPhone had this first!".
So what?
> It’s amazing how quick we are to go ooo ahhh when big tech replicates what is already common place in little tech or academia.
Translation: "You're dumb for liking this thing I had years ago". What an empty comment.
I don't have an Android and never heard of SoundHound, and I'm quick to go "ooo ahhh" because last weekend my mom was humming a song she didn't know the name or words of, and next time I talk to her I can tell her to try song humming on OK Google, and her phone now does this by default, and if it works I'm predicting she will tell some of her friends or sisters as well.
perhaps I should make sure to remind her that she shouldn't be impressed if it works, because a thing she would never have paid that much for, didn't care about and never owned, could do it years ago, would that help?
> Translation: "You're dumb for liking this thing I had years ago". What an empty comment.
That’s just your extremely uncharitable and incorrect insinuation of my comment. What I was saying was not about the user’s reaction to the feature but instead about the admiration of the company. It’s not impressive if Ford uses a wheel on their car because a wheel is old technology that others have already done well.
When you say “we” are too quick to X, but you personally are not Xing, then it is saying “you are too quick to X”.
Is it not impressive that Ford model T became the mass-market car recognisable a hundred years later, because “we’re too quick to ooh and ahh other companies have used wheels before”?
Look at the people in this comments thread saying it made their morning and they found songs from childhood and they’ve been experimenting with foreign songs, and I ask again, what does “I’m not impressed it’s been done before” add? Why do you think that’s a good, useful, comment? so what if it’s been done before?
When the Model T came out, people weren't impressed by the wheel, they were impressed by the low cost of a well-working automobile. I don't think you understand my analogy.
If another company had come out with a low cost well-working automobile 12 years before Ford, then people should not be as impressed by Ford. That's my point.
Why shouldn't they, why is that your point? If an uncharitable read of your comment is that you are mocking people and trying to gain hipster points by knowing about it before it was popular, then maybe a charitable read is that "we are too quick" is a warning of some hazard or danger that happens if we ooh and aahh about things too quickly which (in some way) objectively haven't earned it, by not being first, and that being first is in some way a majorly important criterion. If so, what is it that you are warning about?
What exactly is your problem with people being excited or impressed by something that was done before, which makes it worth a comment?
> Why shouldn't they, why is that your point? If an uncharitable read of your comment is that you are mocking people and trying to gain hipster points by knowing about it before it was popular, then maybe a charitable read is that "we are too quick" is a warning of some hazard or danger that happens if we ooh and aahh about things too quickly which (in some way) objectively haven't earned it, by not being first, and that being first is in some way a majorly important criterion. If so, what is it that you are warning about?
Again, you are completely misinterpreting my comment. Google is a trillion dollar company. It's not impressive that they recreated something a startup was doing 12 years ago.
> What exactly is your problem with people being excited or impressed by something that was done before, which makes it worth a comment?
For the third time, I'm not saying people shouldn't think the feature is cool. They should just IMHO not be heaping praise on Google for it since it's old tech, and perhaps the scrappy startup that did it first a long time ago deserves more of the credit.
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.
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.
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.
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.
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.
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.
While the backend seems great, the Google assistant UI for this on Android is terrible.
For example, long press the home button, say whats this song, hum a song, it gives 3 suggestions, click a suggestion, click the YouTube link to hear it, click twice back to try another one of the three... And Google assistant has lost all state and no longer shows the 3 results. And if I "swipe up to see your snapshot" it crashes and dumps me back at the launcher...
Did they not even test this? Being able to do back and forward navigation without leaving the user on a random screen is like app design 101, and you can totally write unit tests for it.
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
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.
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.
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 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".
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.
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.
SoundHound has had this feature for many years now, it's the main reason why I started using it rather than Shazaam. However we should not underestimate the significance of Google implementing this feature - humming to search songs will become much more mainstream now
These comments remind me of my favorite Reply All episode, in which Alex and PJ team up with the Barenaked Ladies and a studio band to bring one man's epic earworm to life and search to see if the elusive song actually exists. https://gimletmedia.com/shows/reply-all/o2h8bx/158-the-case-....
I 've experienced the same. I've managed to get specific versions of songs (like "I want you to want me" from Zoey's Extraordinary Playlist series rather than the original one from Cheap Trick) and am very impressed with the tool.
Colour me amazed! I saw a video of some buskers which someone shared a week ago and the tune I know but couldn't remember where it was from, it is a waltz and I thought maybe Swan Lake or Nutcracker but after listening to the soundtracks it clearly was not. At some point I was going to work out the melody on the piano (very basic strap line) and use that to search (there are a few sites which offer this and I have had luck with it in the past). But I just tried humming to Google, I have a sore throat after a minor op, have not long got up, and can't hum or hold a tune to save my life, but low and behold it offered up 3 results and it was the second one.
The Second Waltz, Johann Strauss.
Okay, a very famous piece of music, and a very recognizable melody, but I just thought my warble was so far off that most humans wouldn't be able to tell me what it was!
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.
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”
Anecdotally, it's 3/3 for me, one of which was Kids by MGMT. I'm seeing some fairly divergent results here, I wonder if it's highly sensitive to the particular user's voice.
I've gotten about 10 hits of 12, with such diverse things as "Bella Ciao" (Italian song), "Space Oddity" (the first few bars are practically a monotone), the Pink Panther (no words) and Kalasnjikov by Bregovic (random Serbian (?) words that I don't know).
It got MGMT's Kids no problem, and I know I sung out out of tune.
I'm very impressed.
I found out worked better if I use "doo dee doo dee doo" rather than humming.
I wonder how well they handle peoples tendency to sort of drift out of a key. I can see transposing but keeping correct intervals, but what if the intervals are drifting away from true?
The model behind probably doesn't really check for individual notes and their roots. It "listens" like a human listens (people recognize songs when you hum a piece of song, even though it's not correct root/interval/perfect pitch) so your hum doesn't need to be perfectly music-theory-accurate.
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!
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 rang a radio station once. I think the segment was some sort of community help. Anyway I hummed a tune that was from my earliest memory (like when I was 3 or 4). Anyway it turned out to be Elizabethan Serenade based on a couple of callers working it out from my very poor rendition. I'll need to try Google's new tool out
Does anyone remember song tapper?! (I might be misremembering the name)
It was an old web application where you tap the beat of the song you're looking for on your keyboard, and it presents you with a list of close matches. This was way back before smartphones and the AI revolution were a thing!
It tried it a few times, both humming and and using other techniques to better create the sound. Had little luck sadly.
First I tried the Mario theme song, it got it, but with very low confidence and had about equal confidence for a Bone Thugs song lol.
Tried it again with a rock song that was at least popular enough to show up on an official Spotify Playlist for its decade and genre. It got that with pretty good accuracy.
Finally I tried some sludge metal and punk tunes. I can't vocalize the sludge sound worth shit so I'm not shocked it didn't come back with anything, but I'm mildly disappointed it didn't find anything for the relatively simple Choking Victim song I vocalized, but I assume song popularity is a big component.
Cool feature though, unfortunately I can't hold a tune for as long as the snippet it wants lol.
Wow, it's actually surprisingly fun to try to think of songs and hum or make similar noises to try to get google to come up with the right song.
I think I see a future party game. No song repeats, first person to fail to get Google to come up with the correct song while using no real words loses.
I guess they will use this to take down violations of copyrighted songs on youtube. If you sing/cover or song and some author doesnt like it they may strike it. The "Eagles" are known to be like that about their stuff
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 had an idea some years ago to make this app but based around a community of helping others find their song by humming and finding your own songs, i have a 2 year old react-native project with a basic working version [1]
I don't have time to finish it but i would love it if somebody would make this
Anyone remember the website that helped you ID a song by tapping out it out with the space bar? Song Tapper it might have been called, but the site seems to be long dead, sadly.
I'd love for this to improve. I'm a jazz musician, and I know hundreds of tunes, but can't for the life of me remember their names when I'm on the spot. So it's hard for me to suggest a tune when I'm playing with a band.
Kinda sucks. It's decent at recognising the popular songs from 80s and 90s but as soon as I strayed away from that I get no results. It didn't recognize stuff like the national anthem of my country or even Darude Sandstorm.
It also requires to hum for relatively long, sometimes I remember like 5 seconds of a song but the app wants me to keep going for 15.
Gave it the Imperial March, got "dirty by Cristina Aguilara".
Needs work.
It also thinks the tinny reproduction of "Go to sleep little baby" my kids nightlight plays is "Get ur freak on" by Missy Elliott. Which I can definitely hear, but seeing it on my ambient display at 0300 one morning made.me question my sanity.
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'.
I'm wondering how did they construct the dataset to train ML models on it. Did they just recruit "labelers" who hummed for evey song? Or maybe do they have an automated way to detect humming in youtube videos, and later label those with the corresponding song?
Had a song stuck in my head for weeks, I knew the Chorus and could hum it but had no idea. It found it though - Minnie Riperton - Les Fleurs. I'm quite impressed, although it did think it was more likely to be Eiffel 65 - Blue, a song no one should ever search for. :/
Challenge in classical pieces is that various melodies among the polyphony might get caught in my head. I wouldn't expect Google be picking bass lines out of pop songs, so I guess it's fair that I can't search by, e.g. the organ pedal line.
humming is a hit or miss sometimes, but if i played tunes on short videos of skits from social media apps it brings the matching title, a tough competition for /r/NameThatSong/ and /r/tipofmytongue/ :)
What can you do if you have an mp3 of instrumental music whose origin you would like to find but obviously you can't hum it. Any service that takes an audio file and attempts to find the music title/soundtrack?
This is absolutely mind blowing! Tried it from indie to popular Hindi and English songs to way back old Hindi songs and it found the correct match each time. Hats off!
I just tried this with "Heard a Song" by Kero Kero Bonito, in which the singer tries desperately to find the name of a song they heard on the radio. It didn't work :(
0 for 20 on the most popular and recognizable video game music, like the Super Mario Bros theme song. Seems to only work with top 100 yearly tracks with lyrics.
DAMMIT IT WORKS!!! Just found David's song from the Kelly family. In my memory I always though it was an Asian song or something :-) Now this is the kind of progress I like to see in technology. It's about time I'm getting something out of living in the future.
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.
2026: "We have detected copyrighted thoughts. We are sending officers now to repossess your brain. Please lie flat on the ground with your hands upon your head and wait for officers to arrive. If you fail to assume the position you may be fired upon."
Wondering why they've launched this as part of their Search App (and not as a stand-alone app). Maybe they're afraid of (yet another) anti-trust lawsuit?
If they had launched an app, we would have people here complaining about how no one wants to install an app for a tiny functionality, and then when Google would have inevitably canceled the app in a few years because of lack of installs, we'd have posts complaining about how Google pulls the rug from under its apps.
As for those interested in trying it out, the feature is part of Google Assistant.
Google is using their power, money and influence to occupy another niche? They should stick to their search engine and ads and the rest of the company should be ordered to be broken up. They are too big and that gives them unfair advantage in the markets. At very least they should be ordered to pay tax in a way that any normal business pays it. It should also be calculated how much money they made using tax arrangements normal company couldn't afford to do and that money should be confiscated.
[1] https://www.youtube.com/watch?v=rbTsG9jrJsU