{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2XNUMKOLCGTWK332D6OPS6P6OR","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":"00b122c5129408a6ceccd8534816cc96b59d23fc4fa13e37be58acc01b1dcf69","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-05T08:24:22Z","title_canon_sha256":"0fa3d1b4ab4b0e2ffbd375532402be41c477a333c3734f7d8cd378f1308c2efd"},"schema_version":"1.0","source":{"id":"2406.03049","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.03049","created_at":"2026-07-05T08:27:50Z"},{"alias_kind":"arxiv_version","alias_value":"2406.03049v1","created_at":"2026-07-05T08:27:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03049","created_at":"2026-07-05T08:27:50Z"},{"alias_kind":"pith_short_12","alias_value":"2XNUMKOLCGTW","created_at":"2026-07-05T08:27:50Z"},{"alias_kind":"pith_short_16","alias_value":"2XNUMKOLCGTWK332","created_at":"2026-07-05T08:27:50Z"},{"alias_kind":"pith_short_8","alias_value":"2XNUMKOL","created_at":"2026-07-05T08:27:50Z"}],"graph_snapshots":[{"event_id":"sha256:538e6b5ed18841b31a3dc31405c9016f6788deb575cb44e57390d5603bd59aab","target":"graph","created_at":"2026-07-05T08:27:50Z","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/2406.03049/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Simultaneous speech-to-speech translation (Simul-S2ST, a.k.a streaming speech translation) outputs target speech while receiving streaming speech inputs, which is critical for real-time communication. Beyond accomplishing translation between speech, Simul-S2ST requires a policy to control the model to generate corresponding target speech at the opportune moment within speech inputs, thereby posing a double challenge of translation and policy. In this paper, we propose StreamSpeech, a direct Simul-S2ST model that jointly learns translation and simultaneous policy in a unified framework of multi","authors_text":"Min Zhang, Qingkai Fang, Shaolei Zhang, Shoutao Guo, Yang Feng, Zhengrui Ma","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-05T08:24:22Z","title":"StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03049","kind":"arxiv","version":1},"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:dd70fba5b756f1fff63a07a758c47ee6fffc9d59e7ebd52205d5ab46a4c6b521","target":"record","created_at":"2026-07-05T08:27:50Z","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":"00b122c5129408a6ceccd8534816cc96b59d23fc4fa13e37be58acc01b1dcf69","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-05T08:24:22Z","title_canon_sha256":"0fa3d1b4ab4b0e2ffbd375532402be41c477a333c3734f7d8cd378f1308c2efd"},"schema_version":"1.0","source":{"id":"2406.03049","kind":"arxiv","version":1}},"canonical_sha256":"d5db4629cb11a7656f7a1f9cf979fe747866ec545a6e656c4c463989a70a8675","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d5db4629cb11a7656f7a1f9cf979fe747866ec545a6e656c4c463989a70a8675","first_computed_at":"2026-07-05T08:27:50.665414Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:50.665414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z1RS/lGiDOKubedABCtd4J3nJJ97hHDPugar9zDj31NLGqOBb/2Y6IGDwe8w6N00r1nTnYxzTNRj5Hhu6JklCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:50.666050Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.03049","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd70fba5b756f1fff63a07a758c47ee6fffc9d59e7ebd52205d5ab46a4c6b521","sha256:538e6b5ed18841b31a3dc31405c9016f6788deb575cb44e57390d5603bd59aab"],"state_sha256":"1cff7ae261c56543ccb0a0c9004bf4f5bece2e8b99be8e7bb1f817ecd865d1cc"}