I'd like to know if it's possible to handle multiple voices in a TTS Engine. Now I have an simple TTS engine which supports one voice. I'd like to extend it to support multiple voices in the same engine and switch to different voice internally within the engine. I want this just to avoid creating number of projects for each voice based on language or other parameters.
Thanks
Yes, you can. Typically you would do this underneath your ISpObjectWithToken implementation (as described in the TTS Engine Vendor Porting Guide).
Related
I am so confused. I want to build a chatbot like Siri but for my own tasks. It should be able to :
- search on the internet and get answers of questions .
- give people specific information daily.
- discuss with people some scientific phenomenas.
I can't determine what platform should I use to build this chatbot . I thought about using Dialog flow but I can't figure out if it will give me the ability to do that or no. Also I thought about using tensor flow but I think that it will take a very long time so I was wondering if I can achieve what I want with using some thing like dialog flow and not to build it from scratch?
Actually in my opinion, DialogFlow is the best option to build an assistant, it is really easy to build a chatbot to save reminders, to check the weather or to have a simple conversation. DialogFlow has a really powerful tool called webhook that uses Cloud Functions to do the real programming, for example, call google APIs, such as Translate API, or insert data in your Cloud SQL database.
Also, DialogFlow use Machine Learning algorithms to understand the customer, for example, if the client says: "What's the weathe in Barcelona?" It will answer the question correctly.
Another great feature is that it is integrated with multiple technologies, such as, Google Assistant, Amazon Alexa, Cortana, Telegram, Line, Facebook Messenger, etc.
I recommend you to follow this tutorial.
Luis from Microsoft and DialogFlow from Google allow you to build models for natural language processing. These models need to be trained. So the answer is "no", out of the box, these tools do not "search the internet" to discover answers for your intents.
What you need to do is figure out how to train a natural language model, and integrate search data therein. This is bleeding edge AI. And this really is your question; "How do I integrate search with NLP and/or chatbot?"
Both Google and Microsoft let you hook into search. You do not need the dialog tools to do this; you can just pass the query text to do the searching (and let the engine use both ML and heuristic methods to rank results). You mentioned IBM Watson and this is a tool that uses ML modelling to try and answer QnA questions. The Google competition is DeepMind. You can check out those yourself.
But I believe curated content is often the way to go. Tools like Microsoft's QnA Maker let you build these types of applications very easily with little programming required. You can also look into the Azure or Bing search APIs.
And if you are looking to start with a bot from template, there are tons of examples on GitHub for Azure Bot Service and Actions-on-Google. Some even integrate with search and QnA tools. :-)
(And here is the disclaimer. I work for Microsoft. My views do not represent that of my employer.)
I just start playing with wit.ai NLP and Bot Engine but found some difficulties to make it running using the Polish language.
Especially the built-in entities/functions (like wit/number or wit/age-of-person) seem not to work at all.
So here is my question - Does it make any sense to use wit.ai for languages other than English?
or
Can I verify if wit.ai is trained for any particular language?
Good question! Wit currently supports 50 languages: https://wit.ai/blog/2016/04/28/new-languages. Some of them are in Beta like Polish.
Wit relies heavily on machine learning for built-in entities like wit/location. So the more Polish apps (ie more validated expressions) the better it will be.
For some built-in entities like wit/datetime, wit/duration, wit/age-of-person, Wit uses a probabilistic parser that we open sourced here: duckling.wit.ai
Any help from the community is more than welcome... So if you want to participate, don't hesitate to look at the repo and check if your language is covered or needs improvement
Do you know any digital audio workstation that has API? I would like to create application that can generate music based on such programs possibility. This is purely for my own entertainment, I don't mean to make any kind of commercial moves...
There are a couple of different DAW's you can look at that allow you to interface with a variety of languages. The main ones that spring to mind are Reaper and Ableton. As far as I know, Ableton uses python internally and some clever people have found ways of taking advantage of that here;
https://code.google.com/p/liveapi/
The other one is Reaper, which allows you to script its internal features using Python using something called ReaScript;
http://www.reaper.fm/sdk/reascript/reascript.php
Hope that helps.
I am reading articles about Proximity on Windows Phone. I have the following ideea. I have an app that can exchange small messages between two phones through encoded audio. Can I use proximity and replace NFC support with my app that transfer messages using sound. I need only an advice if the NFC usage in proximity can be replaced with any other functionality that can intentionally send certain messages. I want to know if it;s a good ideea to pursue my concept.
Thanks
Unfortunately for you, Windows Phone OS is not a LEGO constructor where you can replace core system services with your own implementation.
At least not with any documented API.
And if you'll use some undocumented APIs, forget about the windows store.
You can probably do that if you're representing an OEM company that builds windows phone devices.
If you're an individual, what you're trying to do might be possible with Android OS. Search for something like "android building custom ROM".
P.S. I think it's a great idea to pursue your concept.
I really miss the simplicity of IR ports in devices.
Very likely, your acoustic pairing could do the job just as good, while requiring no extra hardware.
Anyone knows of a tool like GameSalad for PC in which you don't have to write scripts or anything but just use the existing behaviors and events to create custom game logic?
Thanks
If you are looking for a cross platform game constructor you might want to try Flowlab, which runs in a web browser.
Construct from Scirra is a free, open-source, drag and drop, game engine. There is however talk of them making a paid version of Construct in the future.
I've only used Construct once, so I don't know that much about it, but i do know a lot about GameMaker.
As long as your not trying to do something complicated like a 3D or MMO game, (both of which GameMaker supports, but with major limitarions) I would recommend you use it, especially if your just starting out. GameMaker is one of the easiest if not the easiest programming language to learn. It also teaches good programming skills. As I mentioned before GameMaker uses drag and drop so you can easily transition from the D&D to the progeamming aspect of GameMaker.
As mentioned in the above posts RPG Maker is another popular tool , but it's limited to RPG games, and doesn't allow you to easily transition to an actual programming language. It's also very restrictive in what you can do.
When you feel like getting into some more advanced gaming engines, Blender is a great tool to use for creating 3D games. It can also be used to create 3D modules and has the ability to create animated movies.
I've never used PyGames before, but Python is a easy language to learn, and would probably be the best way to transition from a D&D program to a programming language.
*GameMaker can be extended in functionality with DLLs and Blender can be extended with Python.
So to summarize, GameMaker is a great tool for creating Games. RPG Maker and Construct are other possibilities, but from my view there not as good as GameMaker. when your ready to get out of Drag&Drop gaming engines Blender, PyGames, and GML(Game Maker Language - the advanced part of the GameMaker product) are all great resources.
PlayBits has an interface similar to GameSalad and makes games for Windows Phone 7, using your PC. Here's the link: http://www.playbits.com/?page_id=171
RPG maker here you can find it is a light weight game engine but if you are clever you can make really good apps
In terms of game development for iOS and Mobile development using the Windows platforms you might want to have a look at these two:
http://www.giderosmobile.com
and
http://www.stencyl.com/
Although I haven't, yet, used the Gideros solution, it's targeted specifically for Mobile platform development and has what looks to be a tidy UI with code folding and syntax coloring if you're comfortable with a traditional coding approach.
Stencyl is an interesting product, it sits beyond the capabilities of Gamesalad and uses a blocks metaphor for programming which works well.
Personally, I wouldn't use any tool that has a single platform for output, which is why I stopped using Gamemaker (I'm aware it now has a Macintosh client, but the quality of the application has been terrible and their player isn't much good either.)
If you're looking for GameSalad for Windows you might want to check out our HTML5 game engine Construct 2 which functions in a similar way.
It's also got an event based system with no programming required, and there's an extensive free edition available for you to try out as well.
You can use Yoyo Game's GameMaker:Studio also.
GameMaker is one such tool.
There is also The 3d Gamemaker, by the same people who make other rapid-game-development tools like DarkBasic.