Opened 8 years ago

Last modified 7 years ago

#12819 new enhancement

Implement a speech recognition application

Reported by: richienyhus Owned by: nobody
Priority: normal Milestone: Unscheduled
Component: Applications Version:
Keywords: Cc:
Blocked By: Blocking:
Platform: All

Description

Another form of accessibility assistance is system speech recognition.

Implementations on other systems include: Windows Speech Recognition, Apple Speech and Dictation, KDE Simon, Gnome Vendics.

Voice recognition engines that we can use:

Library Language Licence
​CMU's PocketSphinx C BSD
​CMU's Sphinx3 C BSD
​Kaldi C++ Apache
​Julius C Attribution Assurance

Change History (2)

comment:1 by richienyhus, 8 years ago

Windows and OSX both have a basic ​voice user interface (VUI) by using spoken commands called ​common commands on Windows and ​speakable items on OSX. There was an aborted effort on Gnome called ​Gnome VoiceControl, but Gnome Vendics can handle limited English voice commands.

Edit: there is also ​Voicely (MIT licenced) which could be forked and ported to Haiku, or used as reference for a C++ Haiku implementation.

Last edited 8 years ago by richienyhus (previous) (diff)

comment:2 by mmu_man, 7 years ago

For reference, my ​antique BeOS patch for CMU Sphinx2. Altough the native audio input seems to refer to a DataIOSoundRecorder.h that was probably added in ZETA...

Note: See TracTickets for help on using tickets.