{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:Q3NFBQSJVHGQJ2S54ZUVSRMCXE","short_pith_number":"pith:Q3NFBQSJ","schema_version":"1.0","canonical_sha256":"86da50c249a9cd04ea5de669594582b901f26478b7b23918d37049d7f07d5d06","source":{"kind":"arxiv","id":"2310.16621","version":1},"attestation_state":"computed","paper":{"title":"ArTST: Arabic Text and Speech Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ajinkya Kulkarni, Amirbek Djanibekov, Hanan Aldarmaki, Hawau Olamide Toyin","submitted_at":"2023-10-25T13:20:54Z","abstract_excerpt":"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. "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2310.16621","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-25T13:20:54Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"e62f89582a0c699fdfbd2f2e464c8122536c2a413676cbf108feb5091e03af1c","abstract_canon_sha256":"01dc86f51dd02283e5119d7ff2ca3922d61daf9bc2bf3c1ac9e98ec5060633ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:00.384873Z","signature_b64":"KbQhbf2++EpWGEnCgfkQFP0nOhdujCgmd9oWbtuAUQVGDBBEnmgRBG905v99K9T/PXrmg6HrYVVFyaQrPFrFCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86da50c249a9cd04ea5de669594582b901f26478b7b23918d37049d7f07d5d06","last_reissued_at":"2026-07-05T07:05:00.384427Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:00.384427Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ArTST: Arabic Text and Speech Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ajinkya Kulkarni, Amirbek Djanibekov, Hanan Aldarmaki, Hawau Olamide Toyin","submitted_at":"2023-10-25T13:20:54Z","abstract_excerpt":"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. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16621","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2310.16621/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2310.16621","created_at":"2026-07-05T07:05:00.384486+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.16621v1","created_at":"2026-07-05T07:05:00.384486+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16621","created_at":"2026-07-05T07:05:00.384486+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q3NFBQSJVHGQ","created_at":"2026-07-05T07:05:00.384486+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q3NFBQSJVHGQJ2S5","created_at":"2026-07-05T07:05:00.384486+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q3NFBQSJ","created_at":"2026-07-05T07:05:00.384486+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q3NFBQSJVHGQJ2S54ZUVSRMCXE","json":"https://pith.science/pith/Q3NFBQSJVHGQJ2S54ZUVSRMCXE.json","graph_json":"https://pith.science/api/pith-number/Q3NFBQSJVHGQJ2S54ZUVSRMCXE/graph.json","events_json":"https://pith.science/api/pith-number/Q3NFBQSJVHGQJ2S54ZUVSRMCXE/events.json","paper":"https://pith.science/paper/Q3NFBQSJ"},"agent_actions":{"view_html":"https://pith.science/pith/Q3NFBQSJVHGQJ2S54ZUVSRMCXE","download_json":"https://pith.science/pith/Q3NFBQSJVHGQJ2S54ZUVSRMCXE.json","view_paper":"https://pith.science/paper/Q3NFBQSJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.16621&json=true","fetch_graph":"https://pith.science/api/pith-number/Q3NFBQSJVHGQJ2S54ZUVSRMCXE/graph.json","fetch_events":"https://pith.science/api/pith-number/Q3NFBQSJVHGQJ2S54ZUVSRMCXE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q3NFBQSJVHGQJ2S54ZUVSRMCXE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q3NFBQSJVHGQJ2S54ZUVSRMCXE/action/storage_attestation","attest_author":"https://pith.science/pith/Q3NFBQSJVHGQJ2S54ZUVSRMCXE/action/author_attestation","sign_citation":"https://pith.science/pith/Q3NFBQSJVHGQJ2S54ZUVSRMCXE/action/citation_signature","submit_replication":"https://pith.science/pith/Q3NFBQSJVHGQJ2S54ZUVSRMCXE/action/replication_record"}},"created_at":"2026-07-05T07:05:00.384486+00:00","updated_at":"2026-07-05T07:05:00.384486+00:00"}