Category Archives: Meetings

Testing ATbar – responsive design version

tablets used for testingA group of us met up over lunch to test ATbar on a series of portable devices.  This was very much a ‘beta’ testing session with critical friends.  We filled in a test form and the results were analysed.

 

 

 

Some problems still need to be resolved namely:

  • size of icons on smart phones
  • selecting text for text to speech – Samsung Galaxy with Honeycomb does not work
  • exiting ATbar does not necessarily mean the speech stops
  • Windows tablet using Chrome does not allow for zoom by stretch and pinch
  • iPad with Safari seems to produce variable results,  in particular with text highlighting
  • highlighting text for text to speech is not easy

It is clear that the only way ATbar can work with mobile web browsers is to have the toolbar embedded in the website’s code.  It cannot be added to mobile browsers as a bookmarklet. If the toolbar is embedded the toolbar will load as it does on a desktop browser offering coloured overlays, text to speech and other text enhancements and accessibility options.

Meeting – Speech in and Speech Out!

This afternoon we debated the issues arising with speech recognition research and text to speech (TTS).  Mashael had two very interesting papers that were showing that Sphinx4 is still the place to be when it comes to looking at Arabic speech recognition but the debate about recognition rates with or without diacritics prevails.  In one paper it appeared that rates were higher without diacritic marks.

We then moved over to listen to the impact of diacritic marks with TTS.  Edrees had a web page that showed us how the recordings he had made with his mobile phone of two synthesised voices were clearer without diacritic marks.

اَللُغَةُ اَلعَرَبِيَةِ لُغَةٍ مَجِيْدَةٌ يَتَحَدْثُ بِهَاَ اَلنْاَسُ فِي أَكْثَرِ مَنْ سِتَةٍ وَ عِشْرِيْنَ دْوُلَةٍ حَوُلَ اَلعَاَلَمِ.

اَللُغَةِ اَلعَرَبِيَةِ مُفْرَدَاتُهَاَ غَيْرِ مَحْدُوُدَةٌ وَ تَحْتَوُيِ عَلَىَ عَدْدٍ مِنْ عَلَامَاتِ اَلْتَشْكِيِلِ اَلَتيِ تُمَيُزِ كَلِمَاَتِهْاَ وَ تَجْعَلَهَاَ لُغَةٌ مُعَقْدَةٌ بَعْضَ اَلشْئِ.

 

listen to .amr file with diacritic marks

اللغة العربية لغة مجيدة يتحدث بها الناس في أكثر من ستة و عشرين دولة حول العالم.

اللغة العربية لغة مفرداتها غير محدودة و تحتوي على عدد من علامات التشكيل التي تميز كلماتها وتجعلها لغة معقدة بعض الشئ.

listen to .amr file without diacritic marks

 

Arabic blog explains some of the issues around pronunciation and diacritics in a recent posting called ‘Arabic Diacritics (Al-Tashkeel الـتـشـكـيـــل )‘.

Further comments

I have taken the liberty of including a comment that Mashael made about our meeting in this blog as she has supplied us with some very useful links.

mashael on said: Edit

Hello All :)

After our meeting today me, Mrs. EA, and Edrees

Here are some papers which we think will be of interest

1) Arabic Phonetic Web Sites Platform Using VoiceXML : (Includes implementation of Arabic ASR (using Sphinx) and TTS (Using MBROLA project)
http://ieeexplore.ieee.org/

2)Natural speaker-independent Arabic speech recognition system based on Hidden Markov Models using Sphinx tools (What draws attention of this paper is that the system gives higher accuracy when implemented without diacritics)
http://ieeexplore.ieee.org

3) This a dictation ASR developed by CMU university called EvalDictator (It supports Arabic, but it suffers from some problems. we’ll check how much progress have been archived on the project)
http://www.speech.cs.cmu.edu/sphinx/dictator/

Minutes from the meeting held on 11th July, 2011

A second meeting of the team was held on 11th July in Room 3005

Attending

Fadwa, E.A. Mike, Seb, John and Magnus attended the meeting with apologies from Mashael and Eedres (my fault as the email did not go out)

 Translation

Question  – Should AT Bar logo remain the same? – It was decided until there is a discussion with the  Mada Center that the logo would remain the same.

ATbar Arabic layout

Layout in reverse with Arabic wording for the javascript tool tips. Fix the web heart will be removed

The individual icons were discussed and it was decided to leave them as they are for the moment whilst we await an evaluation from Qatar.  Seb is going to set up a web page with ATbar story board with Arabic text

Fadwa has made 2 versions of tooltips – with and without diacritic marks – A decision needs to be made as to which system is to be used for the entire project.  The lack of or inclusion of diacritic marks has an impact in different ways on different disabilities – which is preferred – with or without?

arabic menu with diacritics

There is a case for only having the diacritic marks on the important letters  – this has been shown to help users with the hidden short vowels.
arabic menu without diacritics

No diacritic marks

Workpackages

– Discussion around each task for Phase One.

FR-IW-01 – Begin work behind the scenes

FR-IW-02 – Fix the Web heart – Remove but consider for Arabic speaking volunteers in the future

FR-IW-03 – Text magnifier – no change

FR-IW-04 – Font changer – Fadwa has read papers on the subject of the best fonts for those who have reading difficulties – these will be added to the blog and we will reduce the number available to users based on the research findings.

FR-IW- 05 – Style Changer can be completed

FR-IW-06 – Spell Checker – Google appears to be closing their freely available services – this needs to be investigated

FR-IW -07 – Dictionary – see above – Wiktionary possibility with additional work

FR-IW -08 – Information for use – will be translated at a later date

FR-IW -09 – Restore Webpage – can be completed

FR-IW -10 – Close ATbar – can be completed

FR-IW -11 – ALT Tags – translation available above.

FR-IW -12 – ATbar information regarding bug tracking, fixes to be on GitHub.

FR-IW -13 – x64 bit installer – Due to be rebuilt with ATKit.

Follow up discussion with David Banes on 25th July

Next meeting to be confirmed due to holidays.