The reviewed record of science sign in
Pith

arxiv: 2310.16621 · v1 · pith:Q3NFBQSJ · submitted 2023-10-25 · cs.CL · cs.AI· cs.SD· eess.AS

ArTST: Arabic Text and Speech Transformer

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:Q3NFBQSJrecord.jsonopen to challenge →

classification cs.CL cs.AIcs.SDeess.AS
keywords arabicspeechartstmodelpre-trainedtaskstextfine-tuned
0
0 comments X
read the original abstract

We present ArTST, a pre-trained Arabic text and speech transformer for supporting open-source speech technologies for the Arabic language. The model architecture follows the unified-modal framework, SpeechT5, that was recently released for English, and is focused on Modern Standard Arabic (MSA), with plans to extend the model for dialectal and code-switched Arabic in future editions. We pre-trained the model from scratch on MSA speech and text data, and fine-tuned it for the following tasks: Automatic Speech Recognition (ASR), Text-To-Speech synthesis (TTS), and spoken dialect identification. In our experiments comparing ArTST with SpeechT5, as well as with previously reported results in these tasks, ArTST performs on a par with or exceeding the current state-of-the-art in all three tasks. Moreover, we find that our pre-training is conducive for generalization, which is particularly evident in the low-resource TTS task. The pre-trained model as well as the fine-tuned ASR and TTS models are released for research use.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.