Well I was looking for some way to translate speech to text offline on a Windows Phone 7, but all I could find is Hawaii which unfortunately needs connection to the internet. I need something that can work independently of the connection - offline.
Is there some kind of a library, service from Microsoft that could help me out with translating speech to text, in an offline mode?
Is there an offline alternative to the Hawaii for the Windows Phone 7?
Not that I am aware of (for Windows Phone 7). Because there is no low-level access to speech APIs, your best bet would be either implementing your own speech recognition engine (max time/effort) - you have direct access to the microphone input, or using a web service (the most plausible option).
Related
I'm working on a research project in which we create a new text-to-speech (TTS) engine, that converts text to spoken audio.
As the engine is already performing good, we try to make it usable by a large number of applications which made us want the engine to show up as a TTS voice on Windows 10.
In Microsoft's developer documentations, all I found was information on how I can use exisiting/already installed voices in my application. However, I didn't find any information on how to implement a voice so that it shows up as a Windows voice and can be used by any application using the Speech SDK or SAPI.
Which interface do I have to implement or what API do I have to connect to in order to get our new TTS engine work with Windows Speech?
I already crawled the documentation of the Microsoft Speech SDK as well as developer sites like https://learn.microsoft.com/en-us/dotnet/api/system.speech.synthesis.ttsengine
You should look at the TTS Engine Vendor Porting Guide. You need to implement ISpTTSEngine, which does all the work, and ISpObjectWithToken, which manages registration and creation.
I guess the question pretty much says it all?
And I would prefer not to access cloud services such as Microsoft Translator and Project Hawaii?
Is there any direct API I can access?
(For metro apps)
I was able to get the Microsoft Speech Platform working on my Windows 7 laptop (both Voice Recognition and Text-to-Speech). You just need to install SDK and the runtime. You can also download additional Voice and Language packs. I would think it should work on Windows 8 as well. Here is a good sample on how to set it up to recognize some basic phrases like "Find restaurants near Seattle".
There are some new APIs for Windows 8.1:
http://msdn.microsoft.com/en-us/library/windows/apps/windows.media.speechsynthesis.aspx
Text-To-Speech sample:
http://code.msdn.microsoft.com/windowsapps/Speech-synthesis-sample-6e07b218
//build video on Channel9:
http://channel9.msdn.com/Events/Build/2013/2-171
There are no Text to Speech or Speech to text libraries available in .Net for Windows 8 apps. System.Speech and such is not available. You will need to roll your own or find compatible 3rd party library.
I use Bing Translator service in my apps, but that has been removed from existance, they brought the text translator services into Azure, but did not bring speech over and they disabled the old website to get API keys for bing translator. Hadn't heard of Project Hawaii before will have to check it out.
Microsoft's speech API seems available in Windows 7. Was it taken out of Windows 8?
You can now Access Bing Services for Windows 8 , the service has been just released and is in Beta1 stage
I see statements on the web about Windows 8 supporting face detection. Is this face detection or face recognition or both? (I don't care so much about recognition.) Is it in an API available inside a WinRT application and/or .Net? Where's the documentation for this API? (MSDN and Google both give me links to Windows Phone 7 stuff.)
There is no built-in API for this in WinRT. You will have to use a web service for this functionality or build one yourself.
can we call inbuilt Windows phone mango voice feature programmatically as in we use Launcher and Choosers.
Is there a way I can use this feature for my Translator application where my application recognises the voices spoken in different languages and convert them to text in that particular language.
Do we have this feature in BING Translator service? if yes then how to use them?
also how to use the INbuilt voice command of my WP mango to build my application?
can we call inbuilt Windows phone mango voice feature progamatically as in we use Launcher and Choosers.
No. There is no speech API for Windows Phone as of right now. See Microsoft TellMe for a upcoming API.
Is there a way i can use this feature for my Translator application where my applictaion recogonises the voices spoken in different languages and convert them to text in that particular language.
No
also how to use the INbuilt voice command of my WP mango to build my application?
You can't.
Not sure if you have found an answer for this, but Wade Wegner from the azure team has a translating and OCR app built using the Bing translation services. I have not tried it, but this seems like something you could use.
I am developing windows mobile application to scan a product barcode by using in built camera. Can you tell me something about barcode reader sdk which are supporting windows mobile 7?
In Windows Phone 7, with the upcoming Mango update, there will be direct access to the camera feed, without having to take a picture of the barcode. Prior to Mango, there is a library that can be downloaded from Codeplex, called ZXIng (Zebra Crossing). http://silverlightzxing.codeplex.com/
Are you developing for Windows Phone, or Windows Mobile? There is no Windows Mobile 7 - with the complete rewrite, the name changed to Windows Phone.
There is always this library (zxing):
http://silverlightzxing.codeplex.com/
It does a pretty decent job, and is able to read a number of different barcodes/qrcodes/and so on.
I updated the link to the silverlight version.
You can see the documentation here:
http://silverlightzxing.codeplex.com/documentation
It's fairly easy to implement, as he's given everything you need for WP7.