{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NQL3YGJ5PEQIFC4SOVFBVQOFMD","short_pith_number":"pith:NQL3YGJ5","schema_version":"1.0","canonical_sha256":"6c17bc193d7920828b92754a1ac1c560d5ef23adf1aef0b9e5d6c3b10bdb67fd","source":{"kind":"arxiv","id":"2407.11745","version":2},"attestation_state":"computed","paper":{"title":"Universal Sound Separation with Self-Supervised Audio Masked Autoencoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"Jinzheng Zhao, Junqi Zhao, Mark D. Plumbley, Qiuqiang Kong, Wenwu Wang, Xubo Liu, Yi Yuan","submitted_at":"2024-07-16T14:11:44Z","abstract_excerpt":"Universal sound separation (USS) is a task of separating mixtures of arbitrary sound sources. Typically, universal separation models are trained from scratch in a supervised manner, using labeled data. Self-supervised learning (SSL) is an emerging deep learning approach that leverages unlabeled data to obtain task-agnostic representations, which can benefit many downstream tasks. In this paper, we propose integrating a self-supervised pre-trained model, namely the audio masked autoencoder (A-MAE), into a universal sound separation system to enhance its separation performance. We employ two str"},"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":"2407.11745","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-07-16T14:11:44Z","cross_cats_sorted":["cs.AI","cs.SD"],"title_canon_sha256":"268bb0f056f2061eb02eda6caa7fd6dc98e44e01f5957d0ec3e0cefd54d72f4f","abstract_canon_sha256":"1c716831aa60155558396857a097792cec1cc58041d32ed38dd7750323546e61"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:47.560745Z","signature_b64":"ofgsbvzJ+qZUf4ScVx4U5VWdMvp8YjGzvQkDHiiyzzh0QGGafkuBhd4rLFry+OtxsfpmHnuvP7yzcLDgz5YSBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c17bc193d7920828b92754a1ac1c560d5ef23adf1aef0b9e5d6c3b10bdb67fd","last_reissued_at":"2026-07-05T09:31:47.560174Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:47.560174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Universal Sound Separation with Self-Supervised Audio Masked Autoencoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"Jinzheng Zhao, Junqi Zhao, Mark D. Plumbley, Qiuqiang Kong, Wenwu Wang, Xubo Liu, Yi Yuan","submitted_at":"2024-07-16T14:11:44Z","abstract_excerpt":"Universal sound separation (USS) is a task of separating mixtures of arbitrary sound sources. Typically, universal separation models are trained from scratch in a supervised manner, using labeled data. Self-supervised learning (SSL) is an emerging deep learning approach that leverages unlabeled data to obtain task-agnostic representations, which can benefit many downstream tasks. In this paper, we propose integrating a self-supervised pre-trained model, namely the audio masked autoencoder (A-MAE), into a universal sound separation system to enhance its separation performance. We employ two str"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11745","kind":"arxiv","version":2},"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/2407.11745/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":"2407.11745","created_at":"2026-07-05T09:31:47.560234+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.11745v2","created_at":"2026-07-05T09:31:47.560234+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11745","created_at":"2026-07-05T09:31:47.560234+00:00"},{"alias_kind":"pith_short_12","alias_value":"NQL3YGJ5PEQI","created_at":"2026-07-05T09:31:47.560234+00:00"},{"alias_kind":"pith_short_16","alias_value":"NQL3YGJ5PEQIFC4S","created_at":"2026-07-05T09:31:47.560234+00:00"},{"alias_kind":"pith_short_8","alias_value":"NQL3YGJ5","created_at":"2026-07-05T09:31:47.560234+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/NQL3YGJ5PEQIFC4SOVFBVQOFMD","json":"https://pith.science/pith/NQL3YGJ5PEQIFC4SOVFBVQOFMD.json","graph_json":"https://pith.science/api/pith-number/NQL3YGJ5PEQIFC4SOVFBVQOFMD/graph.json","events_json":"https://pith.science/api/pith-number/NQL3YGJ5PEQIFC4SOVFBVQOFMD/events.json","paper":"https://pith.science/paper/NQL3YGJ5"},"agent_actions":{"view_html":"https://pith.science/pith/NQL3YGJ5PEQIFC4SOVFBVQOFMD","download_json":"https://pith.science/pith/NQL3YGJ5PEQIFC4SOVFBVQOFMD.json","view_paper":"https://pith.science/paper/NQL3YGJ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.11745&json=true","fetch_graph":"https://pith.science/api/pith-number/NQL3YGJ5PEQIFC4SOVFBVQOFMD/graph.json","fetch_events":"https://pith.science/api/pith-number/NQL3YGJ5PEQIFC4SOVFBVQOFMD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NQL3YGJ5PEQIFC4SOVFBVQOFMD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NQL3YGJ5PEQIFC4SOVFBVQOFMD/action/storage_attestation","attest_author":"https://pith.science/pith/NQL3YGJ5PEQIFC4SOVFBVQOFMD/action/author_attestation","sign_citation":"https://pith.science/pith/NQL3YGJ5PEQIFC4SOVFBVQOFMD/action/citation_signature","submit_replication":"https://pith.science/pith/NQL3YGJ5PEQIFC4SOVFBVQOFMD/action/replication_record"}},"created_at":"2026-07-05T09:31:47.560234+00:00","updated_at":"2026-07-05T09:31:47.560234+00:00"}