{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2XNUMKOLCGTWK332D6OPS6P6OR","short_pith_number":"pith:2XNUMKOL","schema_version":"1.0","canonical_sha256":"d5db4629cb11a7656f7a1f9cf979fe747866ec545a6e656c4c463989a70a8675","source":{"kind":"arxiv","id":"2406.03049","version":1},"attestation_state":"computed","paper":{"title":"StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Min Zhang, Qingkai Fang, Shaolei Zhang, Shoutao Guo, Yang Feng, Zhengrui Ma","submitted_at":"2024-06-05T08:24:22Z","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"},"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":"2406.03049","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-05T08:24:22Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"0fa3d1b4ab4b0e2ffbd375532402be41c477a333c3734f7d8cd378f1308c2efd","abstract_canon_sha256":"00b122c5129408a6ceccd8534816cc96b59d23fc4fa13e37be58acc01b1dcf69"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:50.666050Z","signature_b64":"z1RS/lGiDOKubedABCtd4J3nJJ97hHDPugar9zDj31NLGqOBb/2Y6IGDwe8w6N00r1nTnYxzTNRj5Hhu6JklCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5db4629cb11a7656f7a1f9cf979fe747866ec545a6e656c4c463989a70a8675","last_reissued_at":"2026-07-05T08:27:50.665414Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:50.665414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Min Zhang, Qingkai Fang, Shaolei Zhang, Shoutao Guo, Yang Feng, Zhengrui Ma","submitted_at":"2024-06-05T08:24:22Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03049","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/2406.03049/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":"2406.03049","created_at":"2026-07-05T08:27:50.665477+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.03049v1","created_at":"2026-07-05T08:27:50.665477+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03049","created_at":"2026-07-05T08:27:50.665477+00:00"},{"alias_kind":"pith_short_12","alias_value":"2XNUMKOLCGTW","created_at":"2026-07-05T08:27:50.665477+00:00"},{"alias_kind":"pith_short_16","alias_value":"2XNUMKOLCGTWK332","created_at":"2026-07-05T08:27:50.665477+00:00"},{"alias_kind":"pith_short_8","alias_value":"2XNUMKOL","created_at":"2026-07-05T08:27:50.665477+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.19810","citing_title":"SimulS2ST-Omni: Data-Efficient Streaming Speech-to-Speech Translation via Explicit Trajectory Supervision","ref_index":198,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2XNUMKOLCGTWK332D6OPS6P6OR","json":"https://pith.science/pith/2XNUMKOLCGTWK332D6OPS6P6OR.json","graph_json":"https://pith.science/api/pith-number/2XNUMKOLCGTWK332D6OPS6P6OR/graph.json","events_json":"https://pith.science/api/pith-number/2XNUMKOLCGTWK332D6OPS6P6OR/events.json","paper":"https://pith.science/paper/2XNUMKOL"},"agent_actions":{"view_html":"https://pith.science/pith/2XNUMKOLCGTWK332D6OPS6P6OR","download_json":"https://pith.science/pith/2XNUMKOLCGTWK332D6OPS6P6OR.json","view_paper":"https://pith.science/paper/2XNUMKOL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.03049&json=true","fetch_graph":"https://pith.science/api/pith-number/2XNUMKOLCGTWK332D6OPS6P6OR/graph.json","fetch_events":"https://pith.science/api/pith-number/2XNUMKOLCGTWK332D6OPS6P6OR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2XNUMKOLCGTWK332D6OPS6P6OR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2XNUMKOLCGTWK332D6OPS6P6OR/action/storage_attestation","attest_author":"https://pith.science/pith/2XNUMKOLCGTWK332D6OPS6P6OR/action/author_attestation","sign_citation":"https://pith.science/pith/2XNUMKOLCGTWK332D6OPS6P6OR/action/citation_signature","submit_replication":"https://pith.science/pith/2XNUMKOLCGTWK332D6OPS6P6OR/action/replication_record"}},"created_at":"2026-07-05T08:27:50.665477+00:00","updated_at":"2026-07-05T08:27:50.665477+00:00"}