In this paper, we implement a multilingual Statistical Machine Translation (SMT) system for Arabic-English Translation. Arabic Text can be categorized into standard and dialectal Arabic. These two forms of Arabic differ significantly. Different mono-lingual and multi-lingual hybrid SMT approaches are compared. Mono-lingual systems do always results in better translation accuracy in one Arabic form and poor accuracy in the other. Multi-lingual SMT models that are trained with pooled parallel MSA/dialectal data result in better accuracy. However, since the available parallel MSA data are much larger compared to dialectal data, multilingual models are biased to MSA. We propose in the work, a multi-lingual combination of different mono-lingual systems using an Arabic form classifier. The outcome of the classier directs the system to use the appropriate mono-lingual models (standard, dialectal, or mixture). Testing the different SMT systems shows that the proposed classifier-based SMT system outperforms mono-lingual and data pooled multi-lingual systems.

Speech therapists and researchers are becoming more concerned with the use of computer-based systems in the therapy of speech disorders. In this paper, we propose a computer-based game with a purpose (GWAP) for speech therapy of Egyptian speaking children suffering from Dyslalia. Our aim is to detect if a certain phoneme is pronounced correctly. An Egyptian Arabic speech corpus has been collected. A baseline acoustic model was trained using the Egyptian corpus. In order to benefit from existing large amounts of Modern Standard Arabic (MSA) resources, MSA acoustic models were adapted with the collected Egyptian corpus. An independent testing set that covers common speech disorders has been collected for Egyptian speakers. Results show that adapted acoustic models give better recognition accuracy which could be relied on in the game and that children show more interest in playing the game than in visiting the therapist. A noticeable progress in children Dyslalia appeared with the proposed system.

A major problem with dialectal Arabic speech recognition is due to the sparsity of speech resources. In this paper, a transfer learning framework is proposed to jointly use a large amount of Modern Standard Arabic (MSA) data and little amount of dialectal Arabic data to improve acoustic and language modeling. The Qatari Arabic (QA) dialect has been chosen as a typical example for an under-resourced Arabic dialect. A wide-band speech corpus has been collected and transcribed from several Qatari TV series and talk-show programs. A large vocabulary speech recognition baseline system was built using the QA corpus. The proposed MSA-based transfer learning technique was performed by applying orthographic normalization, phone mapping, data pooling, acoustic model adaptation, and system combination. The proposed approach can achieve more than 28% relative reduction in WER.

In this paper, a framework for long audio alignment for conversational Arabic speech is proposed. Accurate alignments help in many speech processing tasks such as audio indexing, speech recognizer acoustic model (AM) training, audio summarizing and retrieving, etc. We have collected more than 1,400 hours of conversational Arabic besides the corresponding human generated non-aligned transcriptions. Automatic audio segmentation is performed using a split and merge approach. A biased language model (LM) is trained using the corresponding text after a pre-processing stage. Because of the dominance of non-standard Arabic in conversational speech, a graphemic pronunciation model (PM) is utilized. The proposed alignment approach is performed in two passes. Firstly, a generic standard Arabic AM is used along with the biased LM and the graphemic PM in a fast speech recognition pass. In a second pass, a more restricted LM is generated for each audio segment, and unsupervised acoustic model adaptation is applied. The recognizer output is aligned with the processed transcriptions using Levenshtein algorithm. The proposed approach resulted in an initial alignment accuracy of 97.8-99.0% depending on the amount of disfluencies. A confidence scoring metric is proposed to accept/reject aligner output. Using confidence scores, it was possible to reject the majority of mis-aligned segments resulting in alignment accuracy of 99.0-99.8% depending on the speech domain and the amount of disfluencies.