@inproceedings{L16-1116,
 abstract = {Corpus design for speech synthesis is a well-researched topic in languages such as English compared to Modern Standard Arabic, and there is a tendency to focus on methods to automatically generate the orthographic transcript to be recorded (usually greedy methods). In this work, a study of Modern Standard Arabic (MSA) phonetics and phonology is conducted in order to create criteria for a greedy method to create a speech corpus transcript for recording. The size of the dataset is reduced a number of times using these optimisation methods with different parameters to yield a much smaller dataset with identical phonetic coverage than before the reduction, and this output transcript is chosen for recording. This is part of a larger work to create a completely annotated and segmented speech corpus for MSA.
},
 address = {Portorož, Slovenia},
 author = {Nawar Halabi and Mike Wald},
 booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)},
 month = {May},
 pages = {734--738},
 publisher = {European Language Resources Association (ELRA)},
 title = {Phonetic Inventory for an Arabic Speech Corpus},
 url = {https://www.aclweb.org/anthology/L16-1116},
 year = {2016}
}