Project Mission

To make the impossible possible.

SpeechControl is an application that is to be designed to eventually be integrated into any Ubuntu distro (and possibly into any Linux system). It is to incorporate another means of input for the end-user who may be one of a disability or medical ailment. Thus, SpeechControl is to be a powerful accessibility component for Linux systems.

Keep effort to a minimum, re-use existing technology Solve potential issues Build an Accessible application to preform tasks by speech (or normal input) Have the results returned to the user (with information overload protection).

Long term: startrek like communications, dictate a document etc.

SpeechControl will be able to accomplish the following:

• Speech Synthesis: More commonly known at TTS (Text-To-Speech), the voice that communicates with the end-user will be as natural and inviting as technology permits.

• Speech recognition: Using the available tools at our disposal, SpeechControl will be able to comprehend your spoken word.

• Virtual Assistant: Repetitive task guidance improve for faster and smoother process execution.

• Preconfigured Command Execution:

Who we are and what we do

This team is tied to Accessibility

Meetings

Can you all please enter your availability onto Meeting time You can adjust it to your local time zone to see how it looks for you. We will ensure the meeting takes place when the most people are available, and if needed we will cycle meetings in order to allow everyone not having to be attending at 5AM local time.

Meeting Agenda

Please add your topic to be discussed prior to the actual meeting.

If you cannot attend, please make a note here.

Accessible discussion

• Via voice and irc chat Teamspeak / Skype / Mumble.

Code of Conduct

• Get all members to sign.

Use of voice

• As per the lubuntu channels, and the guidance on Catalysts I have have to be devoiced, we can use either Dragoneyes for admin stuff, or chanserv. I hate badges with a passion.phillw

Sign the CoC before 2011-01-01, else hajour will remove you from the team, new member that want to sign up, have to have the CoC signed before they join. This is to ensure the quality of our team and its products.

Simon

• License situation update is the deadline (feb 14th) feasible ?
• if license is possbile then Extendability: API + documentation Scenarios

Proposed Features

• Command
• Execute
• Return results
• Optional: Manage reptitive tasks (e-mail, scheduling, etc.) for enduser.

Components

• Pulse Audio
• Alsa
• OSS
• Dbus
• AT-SPI
• Simon Listens
• vedics
• Julius
• Sphinx
• Sonic
• speech-dispatcher
• espeak
• festival

• OpenMary

• High constrast themes

Artificial Intelligence

• compile a list of general commands
• lexicon breakdown
• command building
• language composition
• lexicon buildup

• Might be useful: http://en.wikipedia.org/wiki/Natural_language_processing

Across the Family

• The solutions should not overly dependent on only one flavour of the ubuntu family, and idealy available to Linux in general.

Progress

• Simon Listens - License issues bedahr

• Julius - port patches + cmake? from simon listens RainCT

• Sonic - speeds speech with openMary waywardgeek

• IRC meeting talking bot MichealH

• OpenMary - library to connect with the openMary server JackyAlcine and Daniel0108

Any Other Business

Minutes From Last Meetings

2010-12-29 22:00 UTC

2010-12-28 22:00 UTC

2010-12-18.

2010-12-10 Initial Project Chat.

Development

Anything development-orientated will be listed below. We'll be developing in Python,C++, and C#. Although Python is our primary language for portability reason, we will still provide the other libraries to expose the projects to other languages.

Projects

• python-openmary

• python-openmary-gtk

• openmary-c++

• openmary-c++-gtk

• openmary-mono

CategoryAccessibility