{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3QZOCBOJORZZZHU2Z6PIQX7RWR","short_pith_number":"pith:3QZOCBOJ","schema_version":"1.0","canonical_sha256":"dc32e105c974739c9e9acf9e885ff1b47d0dbabc54607dc3c2b0a778e5586e7c","source":{"kind":"arxiv","id":"2507.17527","version":3},"attestation_state":"computed","paper":{"title":"Seed LiveInterpret 2.0: End-to-end Simultaneous Speech-to-speech Translation with Your Voice","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jiongchen Xiao, Jun Zhang, Liehao Zou, Lu Lu, Lu Xu, Meng Yang, Ningxin Peng, Nuo Xu, Rong Cao, Rong Ye, Runsheng Yu, Ruofei Zhang, Shanbo Cheng, Shengtao Ma, Shiguang Pan, Sitong Liu, Ting Han, Wanyi Zhang, Wenhao Zhu, Yiming Yu, Yonghui Wu, Yu Bao, Yujiao Du, Yu Lu, Yuxiang Hu, Yuxuan Wang, Zeyang Li, Zhichao Huang","submitted_at":"2025-07-23T14:07:41Z","abstract_excerpt":"Simultaneous Interpretation (SI) represents one of the most daunting frontiers in the translation industry, with product-level automatic systems long plagued by intractable challenges: subpar transcription and translation quality, lack of real-time speech generation, multi-speaker confusion, and translated speech inflation, especially in long-form discourses. In this study, we introduce Seed-LiveInterpret 2.0, an end-to-end SI model that delivers high-fidelity, ultra-low-latency speech-to-speech generation with voice cloning capabilities. As a fully operational product-level solution, Seed-Liv"},"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":"2507.17527","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-23T14:07:41Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"08352b0a8d36a6afca8644b43daea0bca85aae149a20dbf5f18740dc6b515bab","abstract_canon_sha256":"8c4886e5380815558851453ebf2e058429d54cf7b9a64145a41bc32612703eaf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:10.809006Z","signature_b64":"gt1mXAdx05wdsb84Vu+tTwQBeytXaCuRmbSyxwLHjk2f3SOkUZCqKCTl0Ub2G/NZmiVL1Z6WfyEN6a8Zcs6nCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc32e105c974739c9e9acf9e885ff1b47d0dbabc54607dc3c2b0a778e5586e7c","last_reissued_at":"2026-07-05T11:44:10.808437Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:10.808437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Seed LiveInterpret 2.0: End-to-end Simultaneous Speech-to-speech Translation with Your Voice","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jiongchen Xiao, Jun Zhang, Liehao Zou, Lu Lu, Lu Xu, Meng Yang, Ningxin Peng, Nuo Xu, Rong Cao, Rong Ye, Runsheng Yu, Ruofei Zhang, Shanbo Cheng, Shengtao Ma, Shiguang Pan, Sitong Liu, Ting Han, Wanyi Zhang, Wenhao Zhu, Yiming Yu, Yonghui Wu, Yu Bao, Yujiao Du, Yu Lu, Yuxiang Hu, Yuxuan Wang, Zeyang Li, Zhichao Huang","submitted_at":"2025-07-23T14:07:41Z","abstract_excerpt":"Simultaneous Interpretation (SI) represents one of the most daunting frontiers in the translation industry, with product-level automatic systems long plagued by intractable challenges: subpar transcription and translation quality, lack of real-time speech generation, multi-speaker confusion, and translated speech inflation, especially in long-form discourses. In this study, we introduce Seed-LiveInterpret 2.0, an end-to-end SI model that delivers high-fidelity, ultra-low-latency speech-to-speech generation with voice cloning capabilities. As a fully operational product-level solution, Seed-Liv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.17527","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/2507.17527/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":"2507.17527","created_at":"2026-07-05T11:44:10.808502+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.17527v3","created_at":"2026-07-05T11:44:10.808502+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.17527","created_at":"2026-07-05T11:44:10.808502+00:00"},{"alias_kind":"pith_short_12","alias_value":"3QZOCBOJORZZ","created_at":"2026-07-05T11:44:10.808502+00:00"},{"alias_kind":"pith_short_16","alias_value":"3QZOCBOJORZZZHU2","created_at":"2026-07-05T11:44:10.808502+00:00"},{"alias_kind":"pith_short_8","alias_value":"3QZOCBOJ","created_at":"2026-07-05T11:44:10.808502+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11219","citing_title":"Afrispeech Semantics: Evaluating Audio Semantic Reasoning in Spoken Language Models Across Domains and Accents","ref_index":197,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00523","citing_title":"ProactiveLLM: Learning Active Interaction for Streaming Large Language Models","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17255","citing_title":"MLLP-VRAIN UPV system for the IWSLT 2026 Simultaneous Speech Translation task","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09916","citing_title":"Regularized Entropy Information Adaptation with Temporal-Awareness Networks for Simultaneous Speech Translation","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3QZOCBOJORZZZHU2Z6PIQX7RWR","json":"https://pith.science/pith/3QZOCBOJORZZZHU2Z6PIQX7RWR.json","graph_json":"https://pith.science/api/pith-number/3QZOCBOJORZZZHU2Z6PIQX7RWR/graph.json","events_json":"https://pith.science/api/pith-number/3QZOCBOJORZZZHU2Z6PIQX7RWR/events.json","paper":"https://pith.science/paper/3QZOCBOJ"},"agent_actions":{"view_html":"https://pith.science/pith/3QZOCBOJORZZZHU2Z6PIQX7RWR","download_json":"https://pith.science/pith/3QZOCBOJORZZZHU2Z6PIQX7RWR.json","view_paper":"https://pith.science/paper/3QZOCBOJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.17527&json=true","fetch_graph":"https://pith.science/api/pith-number/3QZOCBOJORZZZHU2Z6PIQX7RWR/graph.json","fetch_events":"https://pith.science/api/pith-number/3QZOCBOJORZZZHU2Z6PIQX7RWR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3QZOCBOJORZZZHU2Z6PIQX7RWR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3QZOCBOJORZZZHU2Z6PIQX7RWR/action/storage_attestation","attest_author":"https://pith.science/pith/3QZOCBOJORZZZHU2Z6PIQX7RWR/action/author_attestation","sign_citation":"https://pith.science/pith/3QZOCBOJORZZZHU2Z6PIQX7RWR/action/citation_signature","submit_replication":"https://pith.science/pith/3QZOCBOJORZZZHU2Z6PIQX7RWR/action/replication_record"}},"created_at":"2026-07-05T11:44:10.808502+00:00","updated_at":"2026-07-05T11:44:10.808502+00:00"}