Hello,
The only open-source Arabic ASR that is found up to now is “Arabisc” which was developed by Dr. Hussein Hiyassat et. al
Here is the download link: http://sourceforge.net/projects/arabisc/ (Gives an error at run-time)
But I’m still trying to contact the developer for a full access to the system to download if available.
Here is a full description of their work : http://www.springerlink.com/content/n3658k1758140266/
Hello again,
In addition, these are two PHD students whom are working on developing an Arabic ASR:
1)Mona Saqer working on developing Arabic ASR:
http://munasaqer.info/Presentation.pdf
2)Speech recognition of conversational Arabic
Sarah Al Shareef, Supervisor: Thomas Hain
http://spandh.dcs.shef.ac.uk/projects/phd/
An Investigation on Speech Recognition for Colloquial Arabic
This paper describes a study of grapheme-based speech recognition for colloquial Arabic. An investigation of language and acoustic model configurations is carried out to illustrate the differences between colloquial and modern standard Arabic (MSA) on the example of Levantine telephone conversations. The study defines extensive and carefully crafted data sets for different dialects and studies their overlap with MSA sources. The use of grapheme models is re-investigated, and alternative configuration for acoustic models to correct obvious short-comings are tested. The recognition performance was analyzed on two levels: corpus-level and dialect-level. In addition modifications of dictionaries to allow better specification of sound patterns is explored. Overall the experiments highlight the need for higher level information on acoustic model selection.
Thank you so much for all this help and I am just hoping Seb will be able to work with you to see if any of this code can be used with the toolbar. I am looking forward to chatting again next week and will also try to read the papers before then.
Hi again,
Thank you for your response.
I’ve found this Open Source Dictation System called “EvalDictator” that is mentioned to support Arabic.
It’s described as:
“The Dictator is a desktop application that performs Dictation via automatic speech recognition. It is based on the Sphinx4 recognizer from Carnegie Mellon. Sphinx4 is a state-of-the-art large vocabulary recognizer. The accuracy is as good as anything, and the size and speed are sufficient for a modern PC. It currently supports English, Arabic and Mandarin using the Wall Street Journal and GALE models”
Here is its homepage:
http://www.speech.cs.cmu.edu/sphinx/dictator/
I don’t know up to now how well it suits our project but I’ll search about.
Hello All :)
After our meeting today me, Mrs. EA, and Edrees
Here are some papers which we think will be of intreset
1) Arabic Phonetic Web Sites Platform Using VoiceXML : (Includes implementation of Arabic ASR (using Sphinx) and TTS (Using MBROLA project)
http://ieeexplore.ieee.org/search/freesrchabstract.jsp?tp=&arnumber=4530330&queryText%3Darabic+phonetic+web+sites+platform%26openedRefinements%3D*%26filter%3DAND%28NOT%284283010803%29%29%26searchField%3DSearch+All
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/search/freesrchabstract.jsp?tp=&arnumber=5556829&queryText%3DNatural+Speaker-independent+Arabic+Speech+Recognition+System%26openedRefinements%3D*%26filter%3DAND%28NOT%284283010803%29%29%26searchField%3DSearch+All
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 achived on the project)
http://www.speech.cs.cmu.edu/sphinx/dictator/
Best Wishes,
Mashael
Thank you once again Mashael and I do hope you do not mind, but I have added your really useful links to the actual blog so they can be spotted more easily!