{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KC423N26ANL4MF3LIVVXBX5K2H","short_pith_number":"pith:KC423N26","schema_version":"1.0","canonical_sha256":"50b9adb75e0357c6176b456b70dfaad1c7b1abbfa9185bae8a403238db3fc046","source":{"kind":"arxiv","id":"2202.04774","version":3},"attestation_state":"computed","paper":{"title":"SHAS: Approaching optimal Segmentation for End-to-End Speech Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Gerard I. G\\'allego, Ioannis Tsiamas, Jos\\'e A. R. Fonollosa, Marta R. Costa-juss\\`a","submitted_at":"2022-02-09T23:55:25Z","abstract_excerpt":"Speech translation models are unable to directly process long audios, like TED talks, which have to be split into shorter segments. Speech translation datasets provide manual segmentations of the audios, which are not available in real-world scenarios, and existing segmentation methods usually significantly reduce translation quality at inference time. To bridge the gap between the manual segmentation of training and the automatic one at inference, we propose Supervised Hybrid Audio Segmentation (SHAS), a method that can effectively learn the optimal segmentation from any manually segmented sp"},"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":"2202.04774","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-02-09T23:55:25Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"4a76f947e88662ad17c8d5ac60a0262fd94762e21eebc4bebce6235c9883b63f","abstract_canon_sha256":"17f9e8e4a7cba04703032af03b5a3de6ab7793453312d6d2394017f755782fe8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:37:57.529967Z","signature_b64":"c0wXYIItNweTBqtl4iS3PbERslVckjft28h5N6W5nZEZMlci0S2q9avf+LOoWHWHwL06fCNOkOSil24LRRSiCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50b9adb75e0357c6176b456b70dfaad1c7b1abbfa9185bae8a403238db3fc046","last_reissued_at":"2026-07-05T04:37:57.529476Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:37:57.529476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SHAS: Approaching optimal Segmentation for End-to-End Speech Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Gerard I. G\\'allego, Ioannis Tsiamas, Jos\\'e A. R. Fonollosa, Marta R. Costa-juss\\`a","submitted_at":"2022-02-09T23:55:25Z","abstract_excerpt":"Speech translation models are unable to directly process long audios, like TED talks, which have to be split into shorter segments. Speech translation datasets provide manual segmentations of the audios, which are not available in real-world scenarios, and existing segmentation methods usually significantly reduce translation quality at inference time. To bridge the gap between the manual segmentation of training and the automatic one at inference, we propose Supervised Hybrid Audio Segmentation (SHAS), a method that can effectively learn the optimal segmentation from any manually segmented sp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.04774","kind":"arxiv","version":3},"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/2202.04774/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":"2202.04774","created_at":"2026-07-05T04:37:57.529535+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.04774v3","created_at":"2026-07-05T04:37:57.529535+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.04774","created_at":"2026-07-05T04:37:57.529535+00:00"},{"alias_kind":"pith_short_12","alias_value":"KC423N26ANL4","created_at":"2026-07-05T04:37:57.529535+00:00"},{"alias_kind":"pith_short_16","alias_value":"KC423N26ANL4MF3L","created_at":"2026-07-05T04:37:57.529535+00:00"},{"alias_kind":"pith_short_8","alias_value":"KC423N26","created_at":"2026-07-05T04:37:57.529535+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/KC423N26ANL4MF3LIVVXBX5K2H","json":"https://pith.science/pith/KC423N26ANL4MF3LIVVXBX5K2H.json","graph_json":"https://pith.science/api/pith-number/KC423N26ANL4MF3LIVVXBX5K2H/graph.json","events_json":"https://pith.science/api/pith-number/KC423N26ANL4MF3LIVVXBX5K2H/events.json","paper":"https://pith.science/paper/KC423N26"},"agent_actions":{"view_html":"https://pith.science/pith/KC423N26ANL4MF3LIVVXBX5K2H","download_json":"https://pith.science/pith/KC423N26ANL4MF3LIVVXBX5K2H.json","view_paper":"https://pith.science/paper/KC423N26","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.04774&json=true","fetch_graph":"https://pith.science/api/pith-number/KC423N26ANL4MF3LIVVXBX5K2H/graph.json","fetch_events":"https://pith.science/api/pith-number/KC423N26ANL4MF3LIVVXBX5K2H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KC423N26ANL4MF3LIVVXBX5K2H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KC423N26ANL4MF3LIVVXBX5K2H/action/storage_attestation","attest_author":"https://pith.science/pith/KC423N26ANL4MF3LIVVXBX5K2H/action/author_attestation","sign_citation":"https://pith.science/pith/KC423N26ANL4MF3LIVVXBX5K2H/action/citation_signature","submit_replication":"https://pith.science/pith/KC423N26ANL4MF3LIVVXBX5K2H/action/replication_record"}},"created_at":"2026-07-05T04:37:57.529535+00:00","updated_at":"2026-07-05T04:37:57.529535+00:00"}