{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:IIE5YJY6K53EIK22CXH7EV5MRB","short_pith_number":"pith:IIE5YJY6","schema_version":"1.0","canonical_sha256":"4209dc271e5776442b5a15cff257ac8869f3b36433ad0285b5bf0b95b68b8959","source":{"kind":"arxiv","id":"1909.12163","version":1},"attestation_state":"computed","paper":{"title":"DARTS: Dialectal Arabic Transcription System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmed Ali, James Glass, Sameer Khurana","submitted_at":"2019-09-26T14:46:58Z","abstract_excerpt":"We present the speech to text transcription system, called DARTS, for low resource Egyptian Arabic dialect. We analyze the following; transfer learning from high resource broadcast domain to low-resource dialectal domain and semi-supervised learning where we use in-domain unlabeled audio data collected from YouTube. Key features of our system are: A deep neural network acoustic model that consists of a front end Convolutional Neural Network (CNN) followed by several layers of Time Delayed Neural Network (TDNN) and Long-Short Term Memory Recurrent Neural Network (LSTM); sequence discriminative "},"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":"1909.12163","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-26T14:46:58Z","cross_cats_sorted":[],"title_canon_sha256":"1a4d68e1c788793488d8c6c197f8e935b1c74450647f35ff2e03614ca95cec16","abstract_canon_sha256":"b50cafa224a2d5de1bed16b2a50ac8383d92e4cbc52313188aa99b3f90619dc0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:07:31.687295Z","signature_b64":"ICd5wgNKmbduAPGgtLxQpSShFM6u3PDSMnKypy420wKPw3itp4V7LZpHmK/R5vbKVQwqUI1WKoApCCRJLy6oDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4209dc271e5776442b5a15cff257ac8869f3b36433ad0285b5bf0b95b68b8959","last_reissued_at":"2026-07-05T00:07:31.686907Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:07:31.686907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DARTS: Dialectal Arabic Transcription System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmed Ali, James Glass, Sameer Khurana","submitted_at":"2019-09-26T14:46:58Z","abstract_excerpt":"We present the speech to text transcription system, called DARTS, for low resource Egyptian Arabic dialect. We analyze the following; transfer learning from high resource broadcast domain to low-resource dialectal domain and semi-supervised learning where we use in-domain unlabeled audio data collected from YouTube. Key features of our system are: A deep neural network acoustic model that consists of a front end Convolutional Neural Network (CNN) followed by several layers of Time Delayed Neural Network (TDNN) and Long-Short Term Memory Recurrent Neural Network (LSTM); sequence discriminative "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.12163","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/1909.12163/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":"1909.12163","created_at":"2026-07-05T00:07:31.686961+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.12163v1","created_at":"2026-07-05T00:07:31.686961+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.12163","created_at":"2026-07-05T00:07:31.686961+00:00"},{"alias_kind":"pith_short_12","alias_value":"IIE5YJY6K53E","created_at":"2026-07-05T00:07:31.686961+00:00"},{"alias_kind":"pith_short_16","alias_value":"IIE5YJY6K53EIK22","created_at":"2026-07-05T00:07:31.686961+00:00"},{"alias_kind":"pith_short_8","alias_value":"IIE5YJY6","created_at":"2026-07-05T00:07:31.686961+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.12254","citing_title":"Advancing Arabic Speech Recognition Through Large-Scale Weakly Supervised Learning","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IIE5YJY6K53EIK22CXH7EV5MRB","json":"https://pith.science/pith/IIE5YJY6K53EIK22CXH7EV5MRB.json","graph_json":"https://pith.science/api/pith-number/IIE5YJY6K53EIK22CXH7EV5MRB/graph.json","events_json":"https://pith.science/api/pith-number/IIE5YJY6K53EIK22CXH7EV5MRB/events.json","paper":"https://pith.science/paper/IIE5YJY6"},"agent_actions":{"view_html":"https://pith.science/pith/IIE5YJY6K53EIK22CXH7EV5MRB","download_json":"https://pith.science/pith/IIE5YJY6K53EIK22CXH7EV5MRB.json","view_paper":"https://pith.science/paper/IIE5YJY6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.12163&json=true","fetch_graph":"https://pith.science/api/pith-number/IIE5YJY6K53EIK22CXH7EV5MRB/graph.json","fetch_events":"https://pith.science/api/pith-number/IIE5YJY6K53EIK22CXH7EV5MRB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IIE5YJY6K53EIK22CXH7EV5MRB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IIE5YJY6K53EIK22CXH7EV5MRB/action/storage_attestation","attest_author":"https://pith.science/pith/IIE5YJY6K53EIK22CXH7EV5MRB/action/author_attestation","sign_citation":"https://pith.science/pith/IIE5YJY6K53EIK22CXH7EV5MRB/action/citation_signature","submit_replication":"https://pith.science/pith/IIE5YJY6K53EIK22CXH7EV5MRB/action/replication_record"}},"created_at":"2026-07-05T00:07:31.686961+00:00","updated_at":"2026-07-05T00:07:31.686961+00:00"}