We are less than a month away from the IBM World of Watson main stage
event. On May 5-6th some of the top business leaders, thinkers and
developers will converge in NYC’s Silicon Alley to talk the future of
cognitive computing and how businesses around the world are using IBM
Watson services to fuel next level innovation across different
industries.
Registration is filling up fast and we want to make sure you’re on the list! Here are the top five reasons why we think you should be there:
1. Get access to the IBM Watson Dev team responsible for emerging cognitive services
2. Meet the top IBM executives and developers responsible for IBM Watson break-through technology
3. Preview dozens of commercial apps heading to market
4. See how some of the world’s biggest companies are taking IBM Watson to scale
5. Tons of developers will be onsite to trade insights and learnings including IBM Watson’s first ever hackathon
Take advantage of the early bird rate (ends 4/15) and register today to get you place at IBM World of Watson.
Watson, the IBM supercomputer best known for crushing "Jeopardy!" contestants at their own game, will publish its first-ever cookbook next week, according to CNN Money.
But this is far from an ordinary cookbook. This will be the first cookbook that's co-created by computer algorithms. Around three years ago, IBM began
building an "idea-generating tool" for Watson, which would let the
supercomputer tap into its massive data trove to create new and
interesting ideas and suggestions. IBM immediately thought food would be
a great category for Watson to innovate, since everyone eats and there
are literally countless combinations of meals and flavors. According to the book, IBM taught
Watson all about existing food dishes so it could learn how flavors and
food chemicals interact, combine and contrast. It also learned about
cultural preferences for certain foods and flavors, and it also learned
about nutrition. Once it had enough data, Watson
began spewing out combinations of ingredients, which the Institute of
Culinary Education helped convert those ideas into real dishes used in
the book.
While there
are plenty of meals you might be accustomed to, Watson offers plenty of
novel flavor combinations you probably wouldn't have dreamt of. How
about an Indian burrito? What about Thai quiche? Or maybe some grilled
asparagus on top of some sous vide pig's feet?
Watson came up with thousands of
recipes but eventually narrowed down the options to 100; the book only
contains 65 different recipes, which are sorted by preferences and
dietary constraints, but CNN Money says IBM might have more recipes and
Watson cookbooks on the way.
" Back in November I released a demo application here on my blog showing the IBM Watson QA Service for cognitive/natural language computing connected to the Web Speech API in
Google Chrome to have real conversational interaction with a web
application. It’s a nice demo, but it always drove me nuts that it only
worked in Chrome. Last month the IBM Watson team released 5 new services, and guess what… Speech Recognition and Speech Synthesis are included!
These
two services enable you to quickly add Text-To-Speech or Speech-To-Text
capability to any application. What’s a better way to show them off
than by updating my existing app to leverage the new speech services?
By
leveraging the Watson services it can now run in any browser that
supports getUserMedia (for speech recognition) and HTML5 <Audio>
(for speech playback).
(Full source code available at the bottom of this post)
You can check out a video of it in action below:
If your browser doesn’t support the getUserMedia API or HTML5
<Audio>, then your mileage may vary. You can check where these
features are supported with these links: <Audio>getUserMedia
Warning:
This is targeting desktop browsers – HTML5 Audio is a mess on mobile
devices due to limited codec support and immature APIs.
So how does this all work?
Just like the QA service, the new Text To Speech and Speech To Text services are now available in IBM Bluemix, so you can create a new application that leverages any of these services, or you can add them to any existing application.
I simply added the Text To Speech and Speech To Text services to my existing Healthcare QA application that runs on Bluemix:
IBM Bluemix Dashboard
These services are available via a REST API. Once you’ve added
them to your application, you can consume them easily within any of your
applications.
I updated the code from my previous example in 2 ways: 1) take advantage of the Watson Node.js Wrapper that makes interacting with Watson a lot easier and 2) to take advantage of these new services services.
Watson Node.js Wrapper
Using the Watson Node.js Wrapper, you can now easily instantiate Watson services in a single line of code. For example:
The credentials come from your environment configuration, then you
just create instances of whichever services that you want to consume.
QA Service
The
code for consuming a service is now much simpler than the previous
version. When we want to submit a question to the Watson QA service,
you can now simply call the “ask” method on the QA service instance.
Below
is my server-side code from app.js that accepts a POST submission from
the browser, delegates the question to Watson, and takes the result and
renders HTML using a Jade template. See the Getting Started Guide for the Watson QA Service to learn more about the wrappers for Node or Java.
01.// Handle the form POST containing the question
02.app.post('/ask', function(req, res){
03.
04.// delegate to Watson
05.question_and_answer_healthcare.ask({ text: req.body.questionText}, function (err, response) {
11.// render the template to HTML and send it to the browser
12.returnres.render('response', response);
13.}
14.});
15.});
Compare this to the previous version, and you’ll quickly see that it is much simpler.
Speech Synthesis
At
this point, we already have a functional service that can take natural
language text, submit it to Watson, and return a search result as text.
The next logical step for me was to add speech synthesis using the
Watson Text To Speech Service (TTS). Again, the Watson Node Wrapper and
Watson’s REST services make this task very simple. On the client side
you just need to set the src of an <audio> instance to the URL for
the TTS service:
1
<audiocontrols=""autoplay=""src="/synthesize?text=The text that should generate the audio goes here"></audio>
On
the server you just need to synthesize the audio from the data in the
URL query string. Here’s an example how to invoke the text to speech
service directly from the Watson TTS sample app:
18.// pipe results back to the browser as they come in from Watson
19.transcript.pipe(res);
20.});
The Watson TTS service supports .ogg and .wav file
formats. I modified this sample slightly to return .ogg files for
Chrome and Firefox, and .wav files for other browsers. On the client
side, these are played using the HTML5 <audio> tag. You can see my modifications in the git repository.
Speech Recognition
Now
that we’re able to process natural language and generate speech, that
last part of the solution is to recognize spoken input and turn it into
text. The Watson Speech To Text (STT) service handles this for us. Just like the TTS service, the Speech To Text service also has a sample app, complete with source code to help you get started.
This service uses the browser’s getUserMedia (streaming) API with socket.io on
Node to stream the data back to the server with minimal latency. The
best part is that you don’t have to setup any of this on your own. Just
leverage the code from the sample app. Note: the getUserMedia API isn’t supported everywhere, so be advised.
On the client side you just need to create an instance of the SpeechRecognizer class in JavaScript and handle the result:
01.var recognizer = newSpeechRecognizer({
02.ws: '',
03.model: 'WatsonModel'
04.});
05.
06.recognizer.onresult = function(data) {
07.
08.//get the transcript from the service result data
09.var result = data.results[data.results.length-1];
On
the server, you need to create an instance of the Watson Speech To Text
service, and setup handlers for the post request to receive the audio
stream.
01.// create an instance of the speech to text service
Release on the 04.04.2015 Written by Andrew Trice. More on Andrew here : http://java.dzone.com/users/triceam Link to the article here : http://java.dzone.com/articles/ibm-watson-qa-speech
