{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:547F57JPKE3LUKVJVR6V3F57NB","short_pith_number":"pith:547F57JP","schema_version":"1.0","canonical_sha256":"ef3e5efd2f5136ba2aa9ac7d5d97bf68715ff10d5f2b20a8178e20d80e44c59e","source":{"kind":"arxiv","id":"2006.14348","version":1},"attestation_state":"computed","paper":{"title":"Audeo: Audio Generation for a Silent Performance Video","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MM","cs.SD","eess.AS","eess.IV"],"primary_cat":"cs.CV","authors_text":"Eli Shlizerman, Kun Su, Xiulong Liu","submitted_at":"2020-06-23T00:58:59Z","abstract_excerpt":"We present a novel system that gets as an input video frames of a musician playing the piano and generates the music for that video. Generation of music from visual cues is a challenging problem and it is not clear whether it is an attainable goal at all. Our main aim in this work is to explore the plausibility of such a transformation and to identify cues and components able to carry the association of sounds with visual events. To achieve the transformation we built a full pipeline named `\\textit{Audeo}' containing three components. We first translate the video frames of the keyboard and the"},"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":"2006.14348","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-23T00:58:59Z","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS","eess.IV"],"title_canon_sha256":"5dfb6aaedcad8a2a74d776fbe8f14bdf3cc1270007392c6302a15b1f37067411","abstract_canon_sha256":"de87991661a1f04779aae036603a335b10ec63e35838f291fa1c541a7af9fabe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:49:52.845479Z","signature_b64":"tR1hr/wZgO1KrV5gn8dO9YnLxwJ4w7p3Ust1sQwecnLaZMsO/H8I9mdIHQ9AjFruGS4eGyM4gnV1JoIxACKkBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef3e5efd2f5136ba2aa9ac7d5d97bf68715ff10d5f2b20a8178e20d80e44c59e","last_reissued_at":"2026-07-05T01:49:52.845031Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:49:52.845031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audeo: Audio Generation for a Silent Performance Video","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MM","cs.SD","eess.AS","eess.IV"],"primary_cat":"cs.CV","authors_text":"Eli Shlizerman, Kun Su, Xiulong Liu","submitted_at":"2020-06-23T00:58:59Z","abstract_excerpt":"We present a novel system that gets as an input video frames of a musician playing the piano and generates the music for that video. Generation of music from visual cues is a challenging problem and it is not clear whether it is an attainable goal at all. Our main aim in this work is to explore the plausibility of such a transformation and to identify cues and components able to carry the association of sounds with visual events. To achieve the transformation we built a full pipeline named `\\textit{Audeo}' containing three components. We first translate the video frames of the keyboard and the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.14348","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/2006.14348/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":"2006.14348","created_at":"2026-07-05T01:49:52.845084+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.14348v1","created_at":"2026-07-05T01:49:52.845084+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.14348","created_at":"2026-07-05T01:49:52.845084+00:00"},{"alias_kind":"pith_short_12","alias_value":"547F57JPKE3L","created_at":"2026-07-05T01:49:52.845084+00:00"},{"alias_kind":"pith_short_16","alias_value":"547F57JPKE3LUKVJ","created_at":"2026-07-05T01:49:52.845084+00:00"},{"alias_kind":"pith_short_8","alias_value":"547F57JP","created_at":"2026-07-05T01:49:52.845084+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.20038","citing_title":"Towards Video to Piano Music Generation with Chain-of-Perform Support Benchmarks","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/547F57JPKE3LUKVJVR6V3F57NB","json":"https://pith.science/pith/547F57JPKE3LUKVJVR6V3F57NB.json","graph_json":"https://pith.science/api/pith-number/547F57JPKE3LUKVJVR6V3F57NB/graph.json","events_json":"https://pith.science/api/pith-number/547F57JPKE3LUKVJVR6V3F57NB/events.json","paper":"https://pith.science/paper/547F57JP"},"agent_actions":{"view_html":"https://pith.science/pith/547F57JPKE3LUKVJVR6V3F57NB","download_json":"https://pith.science/pith/547F57JPKE3LUKVJVR6V3F57NB.json","view_paper":"https://pith.science/paper/547F57JP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.14348&json=true","fetch_graph":"https://pith.science/api/pith-number/547F57JPKE3LUKVJVR6V3F57NB/graph.json","fetch_events":"https://pith.science/api/pith-number/547F57JPKE3LUKVJVR6V3F57NB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/547F57JPKE3LUKVJVR6V3F57NB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/547F57JPKE3LUKVJVR6V3F57NB/action/storage_attestation","attest_author":"https://pith.science/pith/547F57JPKE3LUKVJVR6V3F57NB/action/author_attestation","sign_citation":"https://pith.science/pith/547F57JPKE3LUKVJVR6V3F57NB/action/citation_signature","submit_replication":"https://pith.science/pith/547F57JPKE3LUKVJVR6V3F57NB/action/replication_record"}},"created_at":"2026-07-05T01:49:52.845084+00:00","updated_at":"2026-07-05T01:49:52.845084+00:00"}