{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:V4LPX767DMNUQVXPYZLIVBXBWZ","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":"3f1bac112abaa85c54d959de9168fadae7b9256eb4684811a3fb628c7d54cb07","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-07-10T15:15:17Z","title_canon_sha256":"41c337a6a62848667e0cdc1cb4d4c3c35bab9cd2abfca6ab53ce3462d3da0bd2"},"schema_version":"1.0","source":{"id":"2307.04630","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.04630","created_at":"2026-07-05T06:29:15Z"},{"alias_kind":"arxiv_version","alias_value":"2307.04630v1","created_at":"2026-07-05T06:29:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.04630","created_at":"2026-07-05T06:29:15Z"},{"alias_kind":"pith_short_12","alias_value":"V4LPX767DMNU","created_at":"2026-07-05T06:29:15Z"},{"alias_kind":"pith_short_16","alias_value":"V4LPX767DMNUQVXP","created_at":"2026-07-05T06:29:15Z"},{"alias_kind":"pith_short_8","alias_value":"V4LPX767","created_at":"2026-07-05T06:29:15Z"}],"graph_snapshots":[{"event_id":"sha256:6655adb7ac9968385a67994fb8732e4d34e0ea0cc732ec679c4b556639b0711c","target":"graph","created_at":"2026-07-05T06:29:15Z","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/2307.04630/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper describes the NPU-MSXF system for the IWSLT 2023 speech-to-speech translation (S2ST) task which aims to translate from English speech of multi-source to Chinese speech. The system is built in a cascaded manner consisting of automatic speech recognition (ASR), machine translation (MT), and text-to-speech (TTS). We make tremendous efforts to handle the challenging multi-source input. Specifically, to improve the robustness to multi-source speech input, we adopt various data augmentation strategies and a ROVER-based score fusion on multiple ASR model outputs. To better handle the noisy","authors_text":"Guoqing Zhao, Kun Song, Kun Wei, Lei Xie, Ning Jiang, Peikun Chen, Yi Lei, Yiqing Cao, Yongmao Zhang","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-07-10T15:15:17Z","title":"The NPU-MSXF Speech-to-Speech Translation System for IWSLT 2023 Speech-to-Speech Translation Task"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.04630","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:f043a35e42a9c0ac0b5dda1f97d937d29e54e9bf5d72b7d4af6ad97f61ddbfc8","target":"record","created_at":"2026-07-05T06:29:15Z","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":"3f1bac112abaa85c54d959de9168fadae7b9256eb4684811a3fb628c7d54cb07","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-07-10T15:15:17Z","title_canon_sha256":"41c337a6a62848667e0cdc1cb4d4c3c35bab9cd2abfca6ab53ce3462d3da0bd2"},"schema_version":"1.0","source":{"id":"2307.04630","kind":"arxiv","version":1}},"canonical_sha256":"af16fbffdf1b1b4856efc6568a86e1b67be2e1f3f696c516385892e71632e09f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af16fbffdf1b1b4856efc6568a86e1b67be2e1f3f696c516385892e71632e09f","first_computed_at":"2026-07-05T06:29:15.667975Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:29:15.667975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eyq+WDxS0Tm0lnxrOUn2+sxChdJELx+3ID/o3loQ1hBYcGGMHJBfrp658geTniSK/5ar4xCoXtvKuQPltLRsBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:29:15.668473Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.04630","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f043a35e42a9c0ac0b5dda1f97d937d29e54e9bf5d72b7d4af6ad97f61ddbfc8","sha256:6655adb7ac9968385a67994fb8732e4d34e0ea0cc732ec679c4b556639b0711c"],"state_sha256":"6d143425973aa7d0c9f14997a4835dfb1e8f42b22ca737bc5d217d631467df14"}