{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:V4LPX767DMNUQVXPYZLIVBXBWZ","short_pith_number":"pith:V4LPX767","schema_version":"1.0","canonical_sha256":"af16fbffdf1b1b4856efc6568a86e1b67be2e1f3f696c516385892e71632e09f","source":{"kind":"arxiv","id":"2307.04630","version":1},"attestation_state":"computed","paper":{"title":"The NPU-MSXF Speech-to-Speech Translation System for IWSLT 2023 Speech-to-Speech Translation Task","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Guoqing Zhao, Kun Song, Kun Wei, Lei Xie, Ning Jiang, Peikun Chen, Yi Lei, Yiqing Cao, Yongmao Zhang","submitted_at":"2023-07-10T15:15:17Z","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"},"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":"2307.04630","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-07-10T15:15:17Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"41c337a6a62848667e0cdc1cb4d4c3c35bab9cd2abfca6ab53ce3462d3da0bd2","abstract_canon_sha256":"3f1bac112abaa85c54d959de9168fadae7b9256eb4684811a3fb628c7d54cb07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:29:15.668473Z","signature_b64":"eyq+WDxS0Tm0lnxrOUn2+sxChdJELx+3ID/o3loQ1hBYcGGMHJBfrp658geTniSK/5ar4xCoXtvKuQPltLRsBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af16fbffdf1b1b4856efc6568a86e1b67be2e1f3f696c516385892e71632e09f","last_reissued_at":"2026-07-05T06:29:15.667975Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:29:15.667975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The NPU-MSXF Speech-to-Speech Translation System for IWSLT 2023 Speech-to-Speech Translation Task","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Guoqing Zhao, Kun Song, Kun Wei, Lei Xie, Ning Jiang, Peikun Chen, Yi Lei, Yiqing Cao, Yongmao Zhang","submitted_at":"2023-07-10T15:15:17Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.04630","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/2307.04630/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":"2307.04630","created_at":"2026-07-05T06:29:15.668040+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.04630v1","created_at":"2026-07-05T06:29:15.668040+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.04630","created_at":"2026-07-05T06:29:15.668040+00:00"},{"alias_kind":"pith_short_12","alias_value":"V4LPX767DMNU","created_at":"2026-07-05T06:29:15.668040+00:00"},{"alias_kind":"pith_short_16","alias_value":"V4LPX767DMNUQVXP","created_at":"2026-07-05T06:29:15.668040+00:00"},{"alias_kind":"pith_short_8","alias_value":"V4LPX767","created_at":"2026-07-05T06:29:15.668040+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V4LPX767DMNUQVXPYZLIVBXBWZ","json":"https://pith.science/pith/V4LPX767DMNUQVXPYZLIVBXBWZ.json","graph_json":"https://pith.science/api/pith-number/V4LPX767DMNUQVXPYZLIVBXBWZ/graph.json","events_json":"https://pith.science/api/pith-number/V4LPX767DMNUQVXPYZLIVBXBWZ/events.json","paper":"https://pith.science/paper/V4LPX767"},"agent_actions":{"view_html":"https://pith.science/pith/V4LPX767DMNUQVXPYZLIVBXBWZ","download_json":"https://pith.science/pith/V4LPX767DMNUQVXPYZLIVBXBWZ.json","view_paper":"https://pith.science/paper/V4LPX767","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.04630&json=true","fetch_graph":"https://pith.science/api/pith-number/V4LPX767DMNUQVXPYZLIVBXBWZ/graph.json","fetch_events":"https://pith.science/api/pith-number/V4LPX767DMNUQVXPYZLIVBXBWZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V4LPX767DMNUQVXPYZLIVBXBWZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V4LPX767DMNUQVXPYZLIVBXBWZ/action/storage_attestation","attest_author":"https://pith.science/pith/V4LPX767DMNUQVXPYZLIVBXBWZ/action/author_attestation","sign_citation":"https://pith.science/pith/V4LPX767DMNUQVXPYZLIVBXBWZ/action/citation_signature","submit_replication":"https://pith.science/pith/V4LPX767DMNUQVXPYZLIVBXBWZ/action/replication_record"}},"created_at":"2026-07-05T06:29:15.668040+00:00","updated_at":"2026-07-05T06:29:15.668040+00:00"}