Category Archives: Arabic

Updates on the progress on Arabic spell checking, TTS, Word Prediction and the ATKit

footstepsThe last few weeks since the Christmas break have flown by with a flurry of activity which is retrospect seems at times to have made us feel as if we have been going two steps forward only to have to go at least one if not more steps backward!  But there have been some breakthroughs in the areas of Spell checking, Text to Speech, Word Prediction and the ATKit website.

Spell Checking

Thanks to Mashael AlKadi we have a really clear evaluation of the spell checker titled Dyslexic Typing Errors in Arabic (PDF download) and also thank you to Mina Monta who commented that:

  • “Some of the words are correct in spell & in the meaning but AT spell checker detect that those are wrong words
  • In the suggested word list, there is no sorting according to the priority of the suggested word (according to the relativity between the suggested word & the original wrong word)
  • Some of the suggested words are wrong in spell
  • The number of the suggested words is to high comparing with MS Word spell checker.
  • MS Word is better in detecting the wrong words in grammar (the word has correct spell) “

Sadly research into English spell checkers has revealed that they are not as accurate as we had hoped when it comes to providing false errors and real words or homophones as can be seen from this presentation about online spell checking.

Spell checking when working online.

View more presentations from E.A. Draffan.

I asked Mashael whether adding a new corpus would help as Seb has succeeded in collecting a larger Arabic corpus and has put in some code to make it possible to add this extended vocabulary.   However, Mashael’s comment was:

“regarding adding new words, do you mean expanding the tool’s dictionary? I don’t think you should worry beacuse it was working very well expect for certain remarks that I’ve said such as the tool’s behavior with words attached to prepositions. In such case only some adjustments should be applied to the tool’s mechanism and I think it will work great.”

So with the support of Erik and Mina in our last meeting, it has been decided that we will work on particular improvements as a future aim with the help of our Arabic speaking colleagues.

Text to Speech

It has been a bit of a trial and error period starting with the withdrawal of Google Translate. We were aware this might happen, but had rather hoped there could be a reprieve as this was a free option, although in the tests carried out with 5 Arabic speaking students the results were poor in comparison to Acapela and Vocalizer voices. The sadness also on the part of the time spent on this work as it was something we had proved was possible to achieve – a free TTS on the toolbar.  Microsoft Speak Method was also tried and tested – but the TTS appeared to leave off initial sounds and the voice was unacceptable to our beta testers.

We also learnt that NVDA in Arabic was only going to work with the Arabic TTS offered by Microsoft and eSpeak and Festival with the Mbrola project was still an uphill struggle.

As a research project and definitely not for profit we also wondered if we could go back to Google Translate but the agreement  specifically says  “The program may be used only by registered researchers and their teams, and access may not be shared with others.”

Meanwhile Fadwa Mohamad kindly visited King Abdulaziz City for Science and Technology(KACST) over the Christmas period and met Professor Ibrahim A. Almosallam who has been in touch to say that they are developing an Arabic Text to Speech application, but it has yet to be released.  I am enquiring as to whether this is a desktop application or a VAAS system (Voice as a Service) such as that offered by Acapela in Arabic.

Seb then spent time working on the Acapela VAAS system and this was shown to work well in all the tests although there are issues when a whole page is read out.  It is felt that it might be more appropriate to restrict the call on the servers and just allow text to be highlighted and then spoken.  We now have to negotiate the way we can work with this system, as the final output needs to be free to the user.

There is also the option of building a new Arabic voice and this is being explored – although it would take time and effort to generate the corpus, normalise the output and beta test, even when there are engines available to achieve this aim….. A new build Arabic voice needs further discussion but we have the connections in place.

WordPrediction

wordprediction screen grabSeb has been able to show how this feature for the toolbar is possible in English and the background architecture is in place for the Arabic version pending the language pack.

ATKit website

ATkit siteIt has been agreed that the mock up of the ATKit website that was available as a demonstrator should be taken forward and developed.  This has been completed with the ability to add plugins both free and those that require payment (for instance where a TTS requires a fee). Users can register, build  their own toolbar and save the results.  The next step is a completed Arabic translation and the ability to author plugins …

Arabic ATKit

Arabic TTS discussions and success with ATKit beta

TTS logosAs we have all suspected the market for text to speech is now a choice between Nuance and Acapela with eSpeak and Festival offering a very limited choice of languages.  The licences for using options offered by the operating systems such as Microsoft and Apple do not allow us to use these for a browser based toolkit.

So we have been trialling the voice with Google translate but that only works for 1000 characters and is liable to disappear as a service.  We discussed the issue with a Google employee who was not very hopeful that we would be able to pursue this idea further although we would still like to keep this door open.

We also want to continue to see if we can discover any researchers still working on an open source free TTS for Arabic speech, but in the meantime we have been discussing the use of the Acapela Voice As A Service system that also works well as a plug-in for the new ATKit.

The web site for the English version of ATBar using the ATKit system of plug-ins  is ready for testing and final checks for the Arabic version will be set in place with plugins once agreements have occurred regarding the TTS, as all other sections are complete.  We are still looking for suitable dyslexic type errors to improve the present dictionary and have begun the research on both the word prediction and speech recognition.

Finally we have set up a ATKit plugin Google Group for further collaboration in the hope that this can become a truly open innovative process and a case study for the REALISE market place which has just received sponsorship from Devices for Dignity who are interested in seeing how case studies such as the ATKit develop in the future.

Documentation and ATkit Plug-in Progress

ATKit plugins

Seb has recently been working on the documentation and the code behind the plugins for the ATKit making it possible to convert the ATBar into a modular system that allows users to choose which plug-ins they wish to have on the bar.

An example above shows how Readability has been added to list of plug-ins and the code is available on the ATKit wiki.

The spell checking issues appear to have been solved but testing is now at an important stage where we see if it works with sentences other than those we have in our test paragraph!

The free to users Arabic text to speech plug-in has been causing more concern as Acapela and Nuance still reign supreme and these voices can be licensed with the plug-in system,  but the gauntlet has been thrown down to see if we can explore other options!

Spell checking and the Arabic script

The Arabic script is cursive and we have been exploring difficulties with accurate online spell checking. Fadwa Mohamad has kindly shared her knowledge about some of the issues that arise for those with dyslexia when it comes to the way Arabic characters are linked. Arabic has 28 letters to represent 34 phonemes and we have already discussed the issues of vowels and diacritics. Now we have learnt there is the thorny problem that only 22 of the 28 letters have two way connectors. The 6 remaining letters can only be joined in one way – so an Arabic word can contain one of more spaces. This means a word using some of these 6 letters, that can only be joined up in one way, may be divided in several places.

The other problem of note is that capital letters are not used in Arabic, so once again it may not be easy to see or work out where word boundaries occur. This along with the odd spacing obviously causes concerns for some readers, but may also be one reason why a spell checker can appear to gobble letters when it tries to correct a word!

To add to these issues the articles ‘the’,’a’ or ‘an’ in English tend to be joined to the following word in Arabic –  so those who can read Arabic will recognise the letters ‘AL’ or “Arabic: الـ‎, also transliterated as ul- and in some cases il- and el- ” according to Wikipedia. The reader has to also work out whether the ‘AL’ will be silent or voiced in some cases which impacts on text to speech engines and the lack of spacing can affect spell checking.

Finally Arabic letters may be formed in different ways depending on their position in the word.  So a shape may change from its isolated form to one that is different when seen as the initial letter in the word or the medial one or even the final one! This is how arabic-course.com describe the issue.

Arabic letter changes depending on the position in a word


The work to discover how we can overcome the letter gobbling spell checking and the mispronouncing speech synthesis continues!

 

Insight into the issues for open source TTS in Arabic.

Over the summer the team have been investigating the issues around TTS in Arabic and Edrees Abdu Alkinani has completed his MSc report which has made interesting reading as it summarises many of the findings.   It was noted that Arabic TTS synthesis did not have the early successes of European languages due to the limitations in Natural Language Processing (NLP)  and the complexities of using diacritics as substitutes for vowel combinations. However, with the advances in Natural Language Processing (NLP) and Digital Signal Processing (DSP) plus automatic diacrtizers progress is being developed progress has been made in the commercial world where there are now several attractive Arabic synthesised voices as will be seen in an evaluation to follow.

Issue No 1 – Lack of diacritics on web pages.

Arabic diacritics

The Learning Resource - Arabic language

English speakers may wonder at the reasons for the difficulties with Arabic TTS, but it does not take more than a cursory glance at the written language to understand that having 14 different diacritic marks with 34 phonemes, 28 of which are consonants, and only six vowels that the combinations may cause TTS problems. As Eedris pointed out… ” كُتُبْ ” means books and ” كَتَبَ ” means wrote – the only difference you will notice is the type of marks used above the letters.

English vowel sounds

TEFL world wiki - English vowel sounds

This is compared to the English basic 12 vowel sounds with no accents or diacritics even though we may complain about our odd pronunciation of some written words – rough, cough, though, thorough and through – at least some of the letters are different and we cannot leave any out.   Yet this is what is happening with written Arabic on the web – the diacritics are being left out….. Number one problem for a text to speech engine.

Issue No 2 – The differences between the way the TTS is developed and the resulting output.

Research has shown that although there are now a few text to speech engines they are commercial and even these vary in quality.  The MBROLA project links to work carried out in the open source world, but at present it has been impossible to achieve success with the code offered in the various repositories for evaluation purposes.    However, Eedris has supplied the team with these comments based on the demonstrators offered by the various organisations and companies.

  1. MBROLA project
    MBROLA has two Arabic voices as a recorded audio file. The speed of speech is slow, and the quality poor. Moreover, the pronunciation is hard to understand – even for a an Arabic speaker.  The stress pattern is often incorrect and the distinction between words unclear. The most difficult words to understand have letters like, “ أ” ‘A’, “ ض” ‘th’, “ ل” ‘L’.
  2. Acapela Group
    Acapela offers two good quality male and female voices.  The pronunciation for words with and without diacritic marks is understandable, with accurate stress patterns. There are three letters which appear to cause some difficulty  “ ج” ‘j’, “ ا’ ‘a’, “ ك” ‘k’. The pronunciation of numbers in all situations is good.
  3. Nuance Vocalizer
    Nuance provide a very clear male voice with clear pronunciation. The only problem is that the system produces speech without taking into account diacritics. Words which have letters like “ ق” ‘q’, “ ش” ‘sh’, and “ ض” ‘th’ may cause problems but the speed of speech used in the online demo is good. Numbers are not clearly enunciated due to the lack of diacritics.
  4. Loquendo
    Loquendo offer a recording of a male and female voice on their site as the Arabic voice has only be available since October 2010. The system has good sound quality clear speech. The example on the website has diacritic marks but as it is a small sample it is hard to judge the overall quality but it appears to be good.


Issue No 3 – Further Development of eSpeak with Arabic.

The current version of MBROLA does not appear to run with the arabic voice files and there seem to be very few people who have had success.  So this is work in progress…

 


Hunspell forming the basis of the spellchecker in Arabic

There are several spell checkers available as open source applications and much has been said about the quality of their output in English but there appears to be very little research when linked to the Arabic language.  However, Hunspell is used with many word processing packages.

Seb has succeeded in getting it to work with ATbar vers 2 which means that the Kit version is now almost in beta and there is the beginnings of an Arabic spell checker.

arabic spell checking

Internal Alpha testing of the spell checker.

Recent research by Mashael AlKadi using an ATBar simulation.

I have just read an extremely interesting report by Mashael that looks into the issues around creating an Arabic speech recognition module for the ATbar and ATKit.  The report has a very useful analysis about the tools available and some important considerations which we will cover in more detail in the future.

Mashael collected data from 41 Arabic speaking post-graduate, under-graduate and secondary school students.   In brief the results showed that this group of users tended to browse for text (44%) and multimedia content (42%) with only 14% games or shopping and using social networks etc.  Few seemed to know or use off line services (90%) and this was commented upon in the conclusion as being a useful way of working with the toolbar when off line and should be considered in a similar way to the Silverlight approach – saving useful dictation results or working with forms at a later date.

Speech recognition command and control was not felt to always be useful and the group surveyed did not specify a need due to a disability, in fact 80% said they were happy to use the mouse and keyboard for browser control.  However, 35 of the users said they would use speech recognition for language learning, 20 selected translation, 16 school work, 15 web activities and 10 for work based reports.  High accuracy rates were required (90%) with the use of diacritics, despite the fact that these can cause problems for those with visual impairment and for the elderly.  61% felt that it would be useful to save dictated data for re-use.

Other research that Seb found showed that only 1% of websites are available in Arabic and Mashael found that 44% of her participants wanted to be able to use both English and Arabic for data entry and over half (59%) wanted to have text to speech to read back content.  They appeared to require accuracy over a large vocabulary in terms of speech dictation and its use on the web.

Although several users of the prototype ATbar shown by Mashael in the video below wanted extra features most were happy with the basic version and were content with the design and core functionality.  Mashael highlighted the usefulness of the kit approach with the introduction of a Braille API and the need for a flexible approach to language support.

 

About the paper that related to the Arabic suitable fonts for dyslexic people

Hello…

About the paper that related to the Arabic suitable fonts for dyslexic people, you can find this paper in the Media Library of this blog. I already upload it under the name “ICCHP2006_Alwabil” (as a PDF download). The title of this paper is ”

 

Web Design for Dyslexics: Accessibility of Arabic Content

Areej Al-Wabil, Panayiotis Zaphiris, Stephanie Wilson

 

Published in:

 

International Conference on Computers Helping People  with Special Needs (ICCHP), Austria,2006

 

  Thank you

 

Fadwa