{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CANZ6TIL6H4IFOF73KSAZ5V64J","short_pith_number":"pith:CANZ6TIL","schema_version":"1.0","canonical_sha256":"101b9f4d0bf1f882b8bfdaa40cf6bee27f91e05f5a01de474a96b6b27c121508","source":{"kind":"arxiv","id":"2506.16020","version":1},"attestation_state":"computed","paper":{"title":"VS-Singer: Vision-Guided Stereo Singing Voice Synthesis with Consistency Schr\\\"odinger Bridge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Hao Huang, Jichen Yang, Kai Wang, Liang He, Ying Hu, Zijing Zhao","submitted_at":"2025-06-19T04:34:53Z","abstract_excerpt":"To explore the potential advantages of utilizing spatial cues from images for generating stereo singing voices with room reverberation, we introduce VS-Singer, a vision-guided model designed to produce stereo singing voices with room reverberation from scene images. VS-Singer comprises three modules: firstly, a modal interaction network integrates spatial features into text encoding to create a linguistic representation enriched with spatial information. Secondly, the decoder employs a consistency Schr\\\"odinger bridge to facilitate one-step sample generation. Moreover, we utilize the SFE modul"},"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":"2506.16020","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-06-19T04:34:53Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"cc2a64d0b34da1819afc3f405f9991c4fcd148063f397cf916e8172e9c96b1c7","abstract_canon_sha256":"0b762cb355402ded53a7e02d4e7ed3c99c8a315f59b3432e536093bb94a018dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:28.329414Z","signature_b64":"0tZLOVez4TPK5FJXhAYz86tfTVUvnqyXcSZarzF8gsSTfZfHJN5BME7nRvxO5JmsaUCN1AtmLa277Atn252LCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"101b9f4d0bf1f882b8bfdaa40cf6bee27f91e05f5a01de474a96b6b27c121508","last_reissued_at":"2026-07-05T11:24:28.328814Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:28.328814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VS-Singer: Vision-Guided Stereo Singing Voice Synthesis with Consistency Schr\\\"odinger Bridge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Hao Huang, Jichen Yang, Kai Wang, Liang He, Ying Hu, Zijing Zhao","submitted_at":"2025-06-19T04:34:53Z","abstract_excerpt":"To explore the potential advantages of utilizing spatial cues from images for generating stereo singing voices with room reverberation, we introduce VS-Singer, a vision-guided model designed to produce stereo singing voices with room reverberation from scene images. VS-Singer comprises three modules: firstly, a modal interaction network integrates spatial features into text encoding to create a linguistic representation enriched with spatial information. Secondly, the decoder employs a consistency Schr\\\"odinger bridge to facilitate one-step sample generation. Moreover, we utilize the SFE modul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16020","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/2506.16020/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":"2506.16020","created_at":"2026-07-05T11:24:28.328887+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.16020v1","created_at":"2026-07-05T11:24:28.328887+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16020","created_at":"2026-07-05T11:24:28.328887+00:00"},{"alias_kind":"pith_short_12","alias_value":"CANZ6TIL6H4I","created_at":"2026-07-05T11:24:28.328887+00:00"},{"alias_kind":"pith_short_16","alias_value":"CANZ6TIL6H4IFOF7","created_at":"2026-07-05T11:24:28.328887+00:00"},{"alias_kind":"pith_short_8","alias_value":"CANZ6TIL","created_at":"2026-07-05T11:24:28.328887+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.16020","citing_title":"VS-Singer: Vision-Guided Stereo Singing Voice Synthesis with Consistency Schr\\\"odinger Bridge","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CANZ6TIL6H4IFOF73KSAZ5V64J","json":"https://pith.science/pith/CANZ6TIL6H4IFOF73KSAZ5V64J.json","graph_json":"https://pith.science/api/pith-number/CANZ6TIL6H4IFOF73KSAZ5V64J/graph.json","events_json":"https://pith.science/api/pith-number/CANZ6TIL6H4IFOF73KSAZ5V64J/events.json","paper":"https://pith.science/paper/CANZ6TIL"},"agent_actions":{"view_html":"https://pith.science/pith/CANZ6TIL6H4IFOF73KSAZ5V64J","download_json":"https://pith.science/pith/CANZ6TIL6H4IFOF73KSAZ5V64J.json","view_paper":"https://pith.science/paper/CANZ6TIL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.16020&json=true","fetch_graph":"https://pith.science/api/pith-number/CANZ6TIL6H4IFOF73KSAZ5V64J/graph.json","fetch_events":"https://pith.science/api/pith-number/CANZ6TIL6H4IFOF73KSAZ5V64J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CANZ6TIL6H4IFOF73KSAZ5V64J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CANZ6TIL6H4IFOF73KSAZ5V64J/action/storage_attestation","attest_author":"https://pith.science/pith/CANZ6TIL6H4IFOF73KSAZ5V64J/action/author_attestation","sign_citation":"https://pith.science/pith/CANZ6TIL6H4IFOF73KSAZ5V64J/action/citation_signature","submit_replication":"https://pith.science/pith/CANZ6TIL6H4IFOF73KSAZ5V64J/action/replication_record"}},"created_at":"2026-07-05T11:24:28.328887+00:00","updated_at":"2026-07-05T11:24:28.328887+00:00"}