A Transfer Learning Approach for Under-Resourced Arabic Dialects Speech Recognition

A major problem with dialectal Arabic speech recognition is due to the sparsity of speech resources. In this paper, we propose a transfer learning framework to jointly use large amount of Modern Standard Arabic (MSA) data and little amount of dialectal Arabic data to improve acoustic and language modeling. We have chosen the Qatari Arabic (QA) dialect 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.