On 17/01/11 08:55, sajeev.manikk...@nokia.com wrote: > Hi, > > Having speech recognition support in QT will definitely be a good step > looking forward. There are lot of good application use cases and > possibilities as: > Native interface for Phone is speech, and all current/future bearers or > networks default to data transmissions. Application MMI on a phone can > default to speech while converted data can fly across networks... >
Codethink currently has a small research project around this area, looking at what kind of functionality a decent speech API would require. James Thomas (CC'd) who has a lot of experience in this area is heading it up. I'll be sure to report our results to the list. As Dave mentioned, CMU Sphinx is certainly very impressive and good first port of call. One thing I can say from the off-set is if you want general speaker recognition, you want to have a limited grammar. Even NaturallySpeaking can't do decent continuous-speech recognition without some speaker training. For text-to-speech there are a number of existing framework projects from the A11y world should be reviewed for suitability, like kttsd, OpenTTS and speech-dispatcher. HTH, Rob > > Best Regards, > Sajeev Manikkoth > MeeGo SW R&D > Phone: +918040159000 - Ext: 4585 > Hand Phone: +919663311378 > >> -----Original Message----- >> From: meego-dev-boun...@meego.com [mailto:meego-dev-boun...@meego.com] >> On Behalf Of ext Santakivi Topi >> Sent: Monday, January 17, 2011 12:47 PM >> To: Thiago Macieira >> Cc: meego-dev@meego.com >> Subject: Re: [MeeGo-dev] Speech Recognition API for QT? >> >> On 01/17/2011 09:06 AM, Thiago Macieira wrote: >>> On Monday, 17 de January de 2011 09:22:44 Zheng, Huan wrote: >>> > Hi, dear developers >>> > I did a quick search, it looks like there's no speech recognition >> API >>> in QT >>> > yet, am I missing something? Is there any plan to support speech >>> > recognition in QT? >>> >>> You're right, there's no such API. We also have no current plans -- >> speach >>> recognition is not an easy task. >>> >>> But we're open for ideas on how to implement this. >> >> The IVI repos already have PocketSphinx 0.6.1, which is a >> BSD-style licensed speech recognition library. >> >> One possibility could be to move PocketSphinx into the core >> repo and implement a Qt wrapper on top. >> >> More info: >> >> http://cmusphinx.sourceforge.net/ >> http://sourceforge.net/projects/cmusphinx/files/pocketsphinx/0.6.1/ >> >> http://repo.meego.com/MeeGo/builds/trunk/daily/ivi/repos/source/pocketsp >> hinx-0.6.1-2.47.src.rpm >> >> BR, >> Topi >> >> >>> >>> -- >>> Thiago Macieira - thiago (AT) macieira.info - thiago (AT) kde.org >>> Senior Product Manager - Nokia, Qt Development Frameworks >>> PGP/GPG: 0x6EF45358; fingerprint: >>> E067 918B B660 DBD1 105C 966C 33F5 F005 6EF4 5358 >>> >> _______________________________________________ >> MeeGo-dev mailing list >> MeeGo-dev@meego.com >> http://lists.meego.com/listinfo/meego-dev > _______________________________________________ > MeeGo-dev mailing list > MeeGo-dev@meego.com > http://lists.meego.com/listinfo/meego-dev -- Rob Taylor, CTO, Codethink Ltd. - http://codethink.co.uk Twitter: @robtaylor78 - LinkedIn: http://www.linkedin.com/in/robtaylor78 Office: +44 161 236 5575 - Cell: +44 7891 533856 _______________________________________________ MeeGo-dev mailing list MeeGo-dev@meego.com http://lists.meego.com/listinfo/meego-dev
