{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:IOKQW7JRT7IQXZFHAKLUCEQSVQ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e42c1d1efacbca6edbbcaab4112b41030e8ed36df05a2d6b7c482a5a5ab3fc8e","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-03T19:28:36Z","title_canon_sha256":"1edaaf5a83a991bb5551bee9105b68b0bde8d492248066832e852d620a09709f"},"schema_version":"1.0","source":{"id":"2006.02490","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.02490","created_at":"2026-07-05T01:42:14Z"},{"alias_kind":"arxiv_version","alias_value":"2006.02490v2","created_at":"2026-07-05T01:42:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.02490","created_at":"2026-07-05T01:42:14Z"},{"alias_kind":"pith_short_12","alias_value":"IOKQW7JRT7IQ","created_at":"2026-07-05T01:42:14Z"},{"alias_kind":"pith_short_16","alias_value":"IOKQW7JRT7IQXZFH","created_at":"2026-07-05T01:42:14Z"},{"alias_kind":"pith_short_8","alias_value":"IOKQW7JR","created_at":"2026-07-05T01:42:14Z"}],"graph_snapshots":[{"event_id":"sha256:2c08785c33119c6f8036ad4dc87caa452c457be1aa6f8b1565cfc01d851e2c38","target":"graph","created_at":"2026-07-05T01:42:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2006.02490/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One of the main challenges for end-to-end speech translation is data scarcity. We leverage pseudo-labels generated from unlabeled audio by a cascade and an end-to-end speech translation model. This provides 8.3 and 5.7 BLEU gains over a strong semi-supervised baseline on the MuST-C English-French and English-German datasets, reaching state-of-the art performance. The effect of the quality of the pseudo-labels is investigated. Our approach is shown to be more effective than simply pre-training the encoder on the speech recognition task. Finally, we demonstrate the effectiveness of self-training","authors_text":"Juan Pino, Mohammad Javad Dousti, Qiantong Xu, Xutai Ma, Yun Tang","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-03T19:28:36Z","title":"Self-Training for End-to-End Speech Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.02490","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1cdf96068be048b5c538577df49b21b55c98bf1176642f1d634c2db8e9c1ae0c","target":"record","created_at":"2026-07-05T01:42:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e42c1d1efacbca6edbbcaab4112b41030e8ed36df05a2d6b7c482a5a5ab3fc8e","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-03T19:28:36Z","title_canon_sha256":"1edaaf5a83a991bb5551bee9105b68b0bde8d492248066832e852d620a09709f"},"schema_version":"1.0","source":{"id":"2006.02490","kind":"arxiv","version":2}},"canonical_sha256":"43950b7d319fd10be4a70297411212ac2fffd70dd6eeac40c070acddc34382a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"43950b7d319fd10be4a70297411212ac2fffd70dd6eeac40c070acddc34382a8","first_computed_at":"2026-07-05T01:42:14.249227Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:42:14.249227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qE9+2PIfjsDtBlRpoXeZlhXrxmZE3J5ctG2Mx06nryLjrADU3DmuAmWZBC2rAz6OTenpiGeM8I0p0RJJXgkZDA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:42:14.249621Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.02490","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1cdf96068be048b5c538577df49b21b55c98bf1176642f1d634c2db8e9c1ae0c","sha256:2c08785c33119c6f8036ad4dc87caa452c457be1aa6f8b1565cfc01d851e2c38"],"state_sha256":"ace78a647075e47c4164d9f883aed3f61d33e6cad295a3b30a807f7136c776f0"}