I'm working on an application where we want to try a robot voice for user interactions instead of the current Speech Services standard voices.
That would make the application more exciting since our bot will be talking to kids.
The application shall be speaking Brazil Portuguese.
Questions:
Is there a built-in language model that would accomplish that for pt-BR?
If not would it be possible to customize the standard voice via SSML or C#?
Suggestions are also welcome!
You can look into using espeak for generating a robot-sounding voice. You can also do it in SSML using the "range" parameter with the prosody element. Currently only Microsoft (Azure cloud, SAPI5 and WinRT's Windows.Media.Speech) engines support the "range" attribute.
Example:
<speak version="1.0" xml:lang="pt-BR">
<prosody pitch="x-low" range="-100%">All your base are belong to us</prosody>
</speak>
Related
I'm evaluating Watson Virtual Agent, but for Spanish, I see that all the capabilities are "closed" in the sense that cannot include any other sentence for a specific capability.
Using conversations component, during the testing that can be done not programmatically but visually. That feature cannot see it in WVA. Is there any plan for including that?
Thanks, Manuel
Im not sure I follow.
If you create intents/entities/dialogs in conversation, you can utilize them through WVA by connecting your workspace to use custom capabilities.
You are correct that you cannot add your custom capabilities to an existing WVA skill. I would recommend turning off the WVA skill and connecting your custom workspace so you have full control.
I've written an AIML file for a chat bot and I'd like to build an interactive web application which allows me to chat with the bot in the web browser.
Is it possible to achieve this with HTML & Javascript?
There is no short answer on how to write a web application which allows a user to interact with your AIML. Writing such an application from scratch will be much more work then compiling the AIML was.
The easiest option would be to use a pre-built service like PandoraBots which allows you to upload AIML files and interact with them in the web browser. It's free to use the explorer part of website. They also have paid developer options which generates an API to bridge your AIML script and any applications you might want to build. It can be easily connected to work with common chat apps like Google talk ect.
If you decide to build everything from scratch you might want to check out the AIML Interpreter library for nodejs.
UPDATE: Here is a node.js based interpreter that you might find useful https://github.com/mrchimp/surly2
I was looking at AIML too and had similar questions. I just found RiveScript RiveScript and it looks like it fits your need to run javascript based on a match. It is not AIML, but very close. There is also at least one tool to convert from AIML to RiveScript, so I would say this fits your needs within those constraints.
I want to implement a feature that you can scan an image of reality by your phone, you will generate a feature code from the image, and then upload it to cloud service. If the database of cloud service has this code, you can download something related to the image. Now, the main problem with me, I need a system or cloud service to help me to identify the images, I don't want to do too much things, so is there hava an existing cloud service to support me do that? Free or paid are ok.
Microsoft has launched recently a new set of machine-learning APIs called "Project Oxford" that include functionality for face detection and recognition, speech recognition and synthesis, vision and understanding of natural languages
Face APIs provide state-of-the-art algorithms to process face images, like face detection with gender and age prediction, recognition, alignment and other application level features. For more information, see Project Oxford at www.projectoxford.ai/face.
Related Link http://azure.microsoft.com/en-in/marketplace/partners/faceapis/faceapis/
http://www.codeproject.com/Articles/989752/Integrate-Windows-Azure-Face-APIs-in-a-Cplusplus-a
I'm creating a mobile app that runs on iOS, Android, BB and Win7. It's a location-based app and you can join groups and then be able to see the location of other members of the group. That's all fine and good. I'm currently using GAE to manage the groups.
Now I'd like to add the ability for members of the group to chat with each other. No 1-1 IM but 1-many chat room. So when you've accessed a certain group in the app, you can type a message and all other members of that group will be able to see your message. I started down the road of mobile push (APNS, C2DM, etc) but thought there had to be a better way. I only want the messages coming in if the app is actually running anyway, so the important part of mobile push is not important in this case. But I of course don't want to poll either.
So I started looking into XMPP and it seems like the right solution, but I'm new to this technology. I don't want the user to have to already have, or create some online IM presence with some service of his choice. I'd like to just have a "Username" pref in the mobile app and that's all he ever needs to do.
So that's where I really need some help. Can I programatically create a chat room somewhere and ids for the users of the group? Would I need to host my own XMPP server (which I understand will not work with GAE).
Or am I just of course altogether than there's a better solution?
Thanks very much for any help.
Warren
I use QuickBlox.com as a back-end for my application. It has built-in Chat module based on XMPP and also a Messages module which can help you to send cross platform pushes to iOS, Android and WP7.
By the way, chat module supports groups in MUC (multi user chat) and they also have a sample to integrate the chat into our app.
Check http://hosted.im/ there is free plan (5 users) at least you can test it.
Regarding XMPP implementation, you can do what you want but you will need to run your own xmpp server
Servers:
ejabberd
openfire
jabberd
jabberd2
tigase
I don't know if GAE support extension I can't help you here.
Hope this help a little bit.
even the question is little bit old i think this will be useful for other techbees.. :)
You can use Quickblox as your server with registering with them they have different plans for users including free plans.
Also if you want you can maintain your own server.
aSmack is good library for implementing XMPP for android. You can get both the jar and source from the aSmack site. just google it.
But from my own experience its a little bit tough to implement the Multi user Chat..
From within an Apex class, how can I detect the Edition (ie, Group, Professional, Enterprise, Unlimited). More specifically, is there an API to retrieve the capabilities (or lack thereof) for the user's edition?
The problem I am trying to solve is that from the Group/Professional edition, users cannot access the custom Web Services in my app, receiving the error LOGIN_OAUTH_API_DISABLED. Is there a way to detect whether this is going to work from within Apex?
You can use the following SOQL to determine the Organization's license type:
SELECT OrganizationType FROM Organization
For Professional it will return "Professional Edition". This is detailed on the Organization object page.
Are there any specific capabilities you're looking to discover? There's no way to determine the edition (and this would be mostly a red herring if you could). A lot of differences end up being reflected in the data model, and you can discover that using the describe features.
If you want to check from apex if your web services is enabled/available, then you could use apex callouts to try and make a call to it (and FWIW, the error code is from OAuth, and not from your apex web service)