When you experiment with Amazon’s Mechanical Turk, it feels like magic. You toss 500 questions into the ether, and the answers instantly start rolling in from anonymous workers around the world. It was great for getting work done, but who are these people? I’ve seen the demographics, but that was too abstract for me.

Last week, I started a new Turk experiment to answer two questions: what do these people look like, and how much does it cost for someone to reveal their face?

Answer #1. This is what Mechanical Turk looks like (click for full-size):

Answer #2. About $0.50.

Results

Here’s my original request:

Upload a photo of yourself holding a handwritten sign that says “I Turk for …”, filling out why you turk. For example, “I Turk for Cash,” “I Turk for My Kids,” “I Turk to Kill Time,” or whatever else you like. Be honest, be funny, be whatever you like.

As a good faith gesture, here’s my photo.

If you have a webcam, you can simply go to Cameroid to snap a photo from your web browser, download the JPG, and upload it below. (Don’t worry if the text is backwards, I can fix that myself.) DON’T provide any identifiable information, like your name or email, since that’s a violation of MTurk policy.

The result will be used in a collage that can be found on my personal weblog, http://waxy.org. By uploading your image and accepting payment for the image, you give permission to me, Andy Baio, to use your image in all forms and media for any lawful purposes. (That’s just cover-my-ass language. I’m almost certainly only going to restrict it to this one project.) The collage will show up there shortly after the HIT is complete. Thanks, everybody!

I started the task at $.05, but only two people responded in the first 24 hours. (And one of those was Joshua Schachter, who I’d told about the project.) Clearly, that was too low, so I increased it to $.25, receiving only eight submissions in 48 hours. (For reference, all 500 of my Girl Talk tasks were done in about an hour.) Increasing it to $.50 got me 20 more submissions in about 48 hours, after which it started to drop off quickly. I wasn’t about to give dollar bills to random people for their photos, so I ended the experiment there. People aren’t willing to give up their anonymity for cheap.

The final results: 30 people total — 10 women, 20 men. Almost all were white, mostly in their 20s and 30s. 21 said they turked for money, 9 for fun or boredom.

Thanks for pulling back the curtain, Turkers.

There’s something satisfyingly self-referential about watching talented musicians try to play their own music in Rock Band and Guitar Hero. Especially when they’re worse than you.

Here’s a list of every video I could find. Let me know if I missed any.

Anthrax’s Scott Ian, “Madhouse” at Best Buy

“You suck. You’re going to have to write easier songs… 20 years ago.”

Continue reading “Musicians Get Meta in Guitar Hero and Rock Band” →

I’ve experimented with audio transcription lately, but always with big, clumsy humans. I’d happily use cyborgs speech recognition software, but even today, automatic conversion of voice-to-text is still flawed. Naturally, I was intrigued when Google announced they were adding voice searching to their Google Mobile iPhone app.

Google’s flirted with voice-to-text conversion in the past, with GOOG-411 and their Audio Indexing of political videos on YouTube. But this is the first time they’re offering a web-accessible interface for speech conversion, albeit completely undocumented, so I decided to poke around a bit to see what I could find.

Over the last few hours, I’ve been analyzing the traffic proxied through my network, trying to reverse-engineer it to get to something usable, but I’ve hit my limits. I’m posting this with the hopes that someone out there can run with it and find out more.

Behind the Scenes

Here’s what we know so far: When you first start speaking into the microphone, the app opens a connection to Google’s server and starts sending over chunks of audio, almost certainly encoded with the open-source Speex codec.

The waveform image is generated on the phone and displayed along with a “Working” indicator and the adorable “beep-boop” sounds. In the background, a tiny file is being sent as a POST request to http://www.google.com/m/appreq/gmiphone. Here’s what the headers look like:

POST /m/appreq/gmiphone HTTP/1.1

User-Agent: Google/0.3.142.951 CFNetwork/339.3 Darwin/9.4.1

Content-Type: application/binary

Content-Length: 271

Accept: */*

Accept-Language: en-us

Accept-Encoding: gzip, deflate

Pragma: no-cache

Connection: keep-alive

Connection: keep-alive

Host: www.google.com

The response from Google is an even smaller attachment. These two files are the same for every query, so don’t contain any meaningful information.

HTTP/1.1 200 OK

Content-Type: application/binary

Content-Disposition: attachment

Date: Tue, 18 Nov 2008 13:06:53 GMT

X-Content-Type-Options: nosniff

Expires: Tue, 18 Nov 2008 13:06:53 GMT

Cache-Control: private, max-age=0

Content-Length: 114

Server: GFE/1.3

After the audio’s sent to Google, they return an HTML page with the results and a second request is triggered, this time a GET request to clients1.google.com with the converted voice-to-text string.

GET /complete/search?client=iphoneapp&hjson=t&types=t

&spell=t&nav=2&hl=en&q=chicken%20soup HTTP/1.1

User-Agent: Google/0.3.142.951 CFNetwork/339.3 Darwin/9.4.1

Accept: */*

Accept-Language: en-us

Accept-Encoding: gzip, deflate

Pragma: no-cache

Connection: keep-alive

Connection: keep-alive

Host: clients1.google.com

The response is an array of search terms in JSON format, for use in search autocompletion.

["chicken soup",[["http://www.chickensoup.com/","Chicken Soup for the Soul",5,""],["http://www.chickensoupforthepetloverssoul.com/","Chicken Soup for the Pet Lover's Soul",5,""],["chicken soup recipe","489,000 results",0,"2"],["chicken soup for the soul","1,470,000 results",0,"3"],["chicken soup dog food","462,000 results",0,"4"],["chicken soup with rice","467,000 results",0,"5"],["chicken soup diet","453,000 results",0,"6"],["chicken soup from scratch","364,000 results",0,"7"],["chicken soup for the soul quotes","398,000 results",0,"8"],["chicken soup crock pot","604,000 results",0,"9"]]]

Help!

Unfortunately, until we can isolate and decode the audio stream, playing with the voice recognition features is out of reach.

Any ideas on cracking this mystery would be hugely appreciated. Anonymity for Google insiders is guaranteed!

Updates

As several commenters figured out, and confirmed to me by Google, the audio is being sent to Google’s servers for voice recognition. The two binaries I posted above aren’t the actual transmission, and are actually identical for every query, so can be disregarded. Sorry about the red herring.

Gummi Hafsteinsson, product manager for Google’s Voice Search, says, “I can confirm that we split the audio down to a smaller byte stream, which is then sent to Google for recognition, but we can’t really provide any details beyond that.” Responding to my request for a public API, he added, “I appreciate the suggestion to provide voice recognition as a service. Right now we have nothing to announce, but we’ll take this feedback as we look at future product ideas.”

Also, Chris Messina discovered some secret settings in the application’s preferences file, including alternate color schemes and sound sets for “Monkey” and “Chicken.” Beep-boop!

Next step: As Paul discovered in the comments, the Legal Notices page says clearly that the app uses the open-source Speex codec for voice encoding. Can anyone capture and decode the audio being sent to Google?

November 19: I rewrote most of this entry to reflect the new information, since it was confusing new readers.

(Credit: Michael Buchino, also available as a shirt)

Last month, I dissected Girl Talk’s Feed the Animals using the list of samples lovingly collected by hundreds of Wikipedia users. But that was totally unofficial, a crowdsourced attempt to find musical needles in a giant mashup haystack.

Well, the official CDs were shipped out last week to everyone who donated more than $10. Inside, as promised, was the official sample list — a one-page insert with every single sample on the album. Steve Heil was the first to scan it and contact me.

Unfortunately, a huge block of printed small-caps text isn’t very useful for my kind of fun, so I tried throwing into several OCR engines on WeOCR to turn the image into text. Tesseract gave the best results, but it was still a mess that needed quite a bit of cleanup.

Anyway, here it is. The complete list of all 322 samples in Girl Talk’s Feed the Animals, available as a CSV, Excel, or Google Spreadsheets document.

Continue reading “Girl Talk's Feed the Animals: The Official Sample List” →