Interview with Technical Director Thomas Holl

Speech recognition is the exciting new feature at  Babbel. It’s not only fun – it’s also amazingly efficient for learning a new language. But how does it work? I got the low down from our Technical Director Thomas.

Crisi: What does the new speech recognition tool do?

Thomas: Basically, we use pronunciation samples recorded by our native speaking course editors and compare your pronunciation to theirs. As always with Babbel, you get instant feedback. The closer your pronunciation is to this example, the more points you get on a scale from 0 to 100. If you get more than 50 points, you’re good enough to be generally understood.

Crisi: But if you just compare two sounds, is that really speech recognition?

Thomas: Sure, we recognize what you say. We’re now sitting in front of the screen and we are talking but you see that the score is 0 all the time. Now, try saying arrivederci.

Crisi: Arrivederci

Thomas: Nice, 78 points.  Better than Aldo Raine in “Inglorious Basterds” (see details here). Remember the hilarious scene where Brad Pitt is trying to speak Italian? We ran his pronunciation through our analysis and as you might expect he scored pretty low. But I’m digressing, sorry. Back to our little test. Your pronunciation is about 78% exact compared to our reference sample. That’s pretty good.

Crisi: Still, it’s only about comparing sounds, not about understanding what I say.

Thomas: Well, there are different sub-types of speech recognition. One is speech-to-text or voice control. That’s what you’d use to enter text or commands if you can’t use a keyboard. Recognizing words and evaluating their pronunciation is another sub-type, and that’s the technology that makes sense for language learning. We can use it for pronunciation training and for building new interactive exercises.

Crisi: So, what’s the technical challenge in this sub-type of speech recognition?

Thomas: Well, it’s not as easy as it sounds – no pun intended. It’s actually not enough to just compare two sounds. It’s a little like telling how similar two people look in two different photos. The audio samples are usually pretty different: a woman has a higher voice than a man and the tempo of speech also differs a lot. And then you have a number of artifacts…

Crisi: Artifacts?

Thomas: Noises and characteristics that are caused by the environment or the technical setup: rumbling, hissing, other sounds mixing into the voice. Most people don’t have a high-end microphone connected to their computer and in our case we just use the built-in mic on my laptop. The audio quality of what the system is hearing is pretty poor.

Crisi: So to make the speech recognition work properly, our users need to have a good mic and be in a quiet room?

Thomas: No, that’s the point: we can also work with cheap microphones and filter out noise in the immediate environment. That’s part of the challenge.

Crisi: Sounds like a lot of filtering and levelling…

Thomas: Yes, that also, but there’s more: We have to distil the “core” of the voice sample and then match that to the original. To do that, the system needs to figure out when you start and stop speaking. You don’t have to press any key to start and stop recording; we do the matching in real-time.

Crisi: So everything we say into the system here is somehow analyzed?

Thomas: Right. Just look at the level: every sound input is analyzed and matched to the sound we’re looking for. In this case, arrivederci.

Crisi: 55 points

Thomas: Ok, yours is better than mine. But you see that the word was recognized among all the other things we said.

Crisi: Is this unique technology? Are there other software product that do this?

Thomas: There are a number of software products that do have speech recognition. Some of them also are of decent quality.

Crisi: So what’s so special about the Babbel speech recognition?

Thomas: Well, it’s online and works in your browser.

Crisi: Does this mean that everything we say here is sent to the Babbel servers and analyzed there?

Thomas: No, the whole audio processing is done instantly, directly in the browser. We don’t have to send the audio to the server and that’s why we can give instant feedback.

Crisi: Do I have to install a plugin or something?

Thomas: You don’t. It’s all done in Flash. 97% of all browsers have the Flash plugin pre-installed. As we use the latest version, you might have to do an update, but that’s very quick. Other than that, you just need a microphone like the one that’s built into my laptop.

Crisi: Babbel has been online since January 2008. Why did it take so long to add this feature?

Thomas: We needed the new Flash Player 10.1 because before that it wasn’t possible to do audio processing locally. It would have been necessary to either send all the audio to the server for analyses or to use a custom browser plugin.

Crisi: What’s wrong with a custom browser plugin?

Thomas: First of all, you have to install new software on your computer. And then you have compatibility issues. There are some rare solutions that offer real-time speech recognition in a browser plugin, but most of them won’t work on your Mac and none of them are compatible with all browsers. Flash is already there, the plugin works fine and it’s available for all platforms.

Crisi: How about the iPhone? You can’t use Flash technology on that platform, can you?

Thomas: No, but the Babbel iPhone apps work natively on the iPhone anyway.

Crisi: Natively?

Thomas: The Babbel apps are built specifically for the iPhone and don’t need a browser or plugin to work. That’s called a “native” application. We can build our algorithm directly into the app.

Crisi: That’s not related to Native Instruments, the software company you used to work for?

Thomas: (laughs): No, not directly. But for being an audio software company, Native Instruments definitely is a great name because the software works natively on the computer.

Crisi: I guess we don’t have to understand that completely. But speaking of audio software: has your audio expertise (along with that of the other Babbel founders) been crucial for this new feature or is it something entirely different than building DJ tools?

Thomas: Both. Of course working on beat detection and time stretching for music and building a speech recognition tool are two different things. On the other hand, we couldn’t have done this in-house without our background.

Crisi: So who actually implemented the new feature?

Thomas: Most of it was done by Toine Diepstraten, one of the Babbel founders. He and I started working together on audio software in our first company, d-lusion, more than 10 years ago. Toine is one of the best developers and audio specialists I’ve ever met. It’s fantastic to have him on board for this project. He did have to do quite some research but without his expertise, this would never have been possible. But this way we have state-of-the art technology that can compare with any other implementation.

Crisi: You sound very convinced

Thomas: From a technical point of view, this is a great piece of software. We actually got some recognition from Adobe, the makers of the Flash Player. They were pretty impressed by our solution.

Crisi: Will this be a focus for Babbel from now on, or do you plan to work on other types of features?

Thomas: It is a very important feature because now we can do everything online that traditional e-learning software can do locally. And we don’t need installation or updates and we have a very lively online community that goes together with the self-directed learning…

Crisi: But?

Thomas: It’s important but it’s not the end. We’ll keep working and adding new features.

Crisi: Can you say what’s next for Babbel?

Thomas: Sorry, but for that we’ll have to turn off the mic.

Crisi: No problem.
–

It’s called learning to “speak” a language, but the sad truth is, few self-directed learners get up the courage to actually open their mouths. Lack of speaking practice can lead to shying away from having interactions with real people, which certainly doesn’t help with the final goal of communication.

The idea of our new integrated speech recognition tool, however, is to get learners talking. By prompting the learner to say the words out loud and test their own pronunciation, Babbel now has covered all the bases for truly effective  foreign language learning: reading, writing, listening comprehension and speaking.

Some traditional e-learning software includes this sort of tool, but none of them do it online in quite the same way. We have built a tool that performs speech recognition in real-time without requiring a custom browser plugin. The technology is complex, but using it is easy. For some backgrounds, check out the interview with Technical Director Thomas Holl.

To try out the speech recognition tool, just log into Babbel.com, set up the audio in 2 quick steps, and start any vocabulary package or beginner’s course. If you don’t have a user account yet, you can register for free and take one trial lesson. Speak up!

]]> http://blog.babbel.com/practice-your-pronunciation-new-speech-recognition-tool/feed/ 4 http://blog.babbel.com/full-english-grammar-course-online/ http://blog.babbel.com/full-english-grammar-course-online/#comments Tue, 21 Jul 2009 11:37:33 +0000 Babbel http://blog.babbel.com/?p=887

Economies may grow or contract, travel may fluctuate or decline, but one thing seems to stay constant around the world: People want to learn English. Their motivation varies. It may be a matter of career, an aching to sing along with current music, or just the desire to engage in an international dialogue that, like it or not, is often going on in what has become a de facto lingua franca. But learning English is still tough, and let’s face it, can be kind of boring – especially when it comes to sorting out the finer points of speaking correctly.

But we at Babbel.com have perhaps done the impossible: we’ve made learning English grammar fun. Based on tried-and-true materials by the respected British publisher Collins, we’ve created a full, interactive online course that is not only modern and effective, but virtually pain-free. “English Grammar: Practise the Basics” uses our unique, intuitive and entertaining approach to help those still in the early stages to build their skills and confidence – at their own pace, without the expected hair-tearing or embarrassment.

We also understand that often a major discouragement for learners is the cost of quality teaching. That’s why we’re offering access to the course – currently made up of 20 tutorials and constantly growing. It’s available anywhere, anytime, and can be canceled whenever. There’s an introductory trial tutorial, “This or That,” for free, and then a 20-day money-back guarantee. Click here, register easily if you haven’t already – don’t forget to set your learning language to English – and try out the free preview. For our press release, click here.

]]> http://blog.babbel.com/full-english-grammar-course-online/feed/ 5 http://blog.babbel.com/mini-vocab-packages-for-the-last-minute-language-learner/ http://blog.babbel.com/mini-vocab-packages-for-the-last-minute-language-learner/#comments Tue, 07 Jul 2009 15:45:55 +0000 Babbel http://blog.babbel.com/?p=848

There’s always a little bit of anxiety that comes along with traveling abroad, whether for business or for pleasure. Possible scenario, night before — for example — the flight to Berlin, a sudden pang:  “Oh right, they speak German in Germany, and I don’t even know how to say ‘how are you’.  How am I going to manage to order my morning coffee?!?”

We at Babbel have now developed a stress-reducing linguistic survival kit (and perhaps path to that caffeine fix in a foreign country) for the last-minute language learner: the Mini-Vocab Package. Compiled especially for the spontaneous traveler, it offers essential words and phrases – in German, French, Spanish, Italian and English – to get through that first encounter with the locals unscathed.

For those who’ve got a little more time before the big trip, besides the Mini-Vocab, there are twenty other in-depth  packages for all relevant situations while traveling, from leaving the airport to arriving at the car rental desk.  There is of course also the opportunity to hook up with someone from Babbel’s now more than 350,000-strong community to chat, trade travel tips or set up a language exchange.

To go directly to the newly compiled Mini-Vocab package, click here. If you are not already registered at Babbel, after a quick and easy registration you will be taken straight through to travel vocabulary.  For our press release, click here.

Babbel’s up for “Best European Web Application or Service” and “Best Design” at TechCrunch’s award The Europas. TechCrunch wants to determine the most innovative tech companies and startups across Europe, Africa and the Middle East. Voting closed on Wednesday, July 1st so let’s see what the results are. Thanks to all who voted for Babbel!

Update July 6th: Babbel made it into the shortlist in both categories, “Best Design” and “Best Web Application Or Service”. Thanks to everyboy who voted!

We’re very pleased that we’ve been selected to present for the start-up track this year at Next09, which will take place in Hamburg May 5 and 6. Next is an annual networking and trend conference for the European web industry.

The theme  of the conference this year really resounds with Babbel: the idea is “Shared Economy”. The basic concept is that the more businesses share their success, the more they can ultimately profit – an idea the we too share!  Markus Witte, Managing Director and one of our founders, will present Babbel to some of the other 1500 participants, familiarizing them with our experiments with a “freemium” model and the fun of learning while helping one another out on the Babbel platform.

We’re excited to announce that we’ve just released a full introductory Spanish course for native speakers of German. The German title of the course is “Spanisch – Der leichte Einstieg” (Spanish – the easy start). Made up of twenty “Tutorials,” it offers a compact and entertaining introduction to the language in the Babbel-style, meaning a unique combination of multi-media fill-in-the-blanks, writing exercises and overall intuitive language learning. This is our first foray into Premium content: for a one-time fee of 19 euros, users can get a 20-part course that packs in a good deal of the linguistic equipment one would need for the next trip without taking up a centimeter of suitcase! A trial of the first Tutorial to get a taste of the entire course is free and non-binding.

For this premium course, we’ve teamed up with renowned German publisher Hueber. Based on Hueber’s book “Spanisch Ganz Leicht in 20 Tagen” (Spanish Made Easy in 20 Days) by Christoph Kehr, “Spanisch – Der leichte Einstieg” is just the beginning of a series of cooperations with different publishers. The rest of Babbel’s content, meanwhile, the vocabulary and writing exercises, as well as access to the website’s 250,000-strong online community, will remain free as always.

Polyglot happy wishes to Babbel.com that hasn’t stopped talkin’ since it launched in January 15, 2008! (Pictured at a little birthday shindig from a hazy last night in Berlin above.) Have any multilingual birthday wishes? Comment away… and check out some of behind the scenes features below to see a bit more how the intuitive, interactive language learning platform ticks. Alles Gute zum Geburtstag, happy Bday, feliz cumpleaños, joyeaux anniversaire, buon compleanno!