{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:A4YK4IJWWA24Q5XJNV4VFAUGMS","short_pith_number":"pith:A4YK4IJW","schema_version":"1.0","canonical_sha256":"0730ae2136b035c876e96d7952828664bc42fe037613d178f46255bded5dae56","source":{"kind":"arxiv","id":"2409.13152","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Audio-Only Data for Text-Queried Target Sound Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Fran\\c{c}ois G. Germain, Gordon Wichern, Janek Ebbers, Jonathan Le Roux, Kohei Saijo, Sameer Khurana","submitted_at":"2024-09-20T01:31:29Z","abstract_excerpt":"The goal of text-queried target sound extraction (TSE) is to extract from a mixture a sound source specified with a natural-language caption. While it is preferable to have access to large-scale text-audio pairs to address a variety of text prompts, the limited number of available high-quality text-audio pairs hinders the data scaling. To this end, this work explores how to leverage audio-only data without any captions for the text-queried TSE task to potentially scale up the data amount. A straightforward way to do so is to use a joint audio-text embedding model, such as the contrastive langu"},"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":"2409.13152","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-20T01:31:29Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"0d93eea6b5e6b6f79d73c2b342060db979a70129ea2d70b02ab5f0a76402f47a","abstract_canon_sha256":"e171aea47a2eec776d482c6f8c312c45d7a4c189b0de41a45d977c4f24bad394"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:30.195407Z","signature_b64":"Zdp8Sve3i0TD5C5wkhyHo9Uwt+2Q4Wy2eDYzExox6+qcan08gTOyuzUqJ4ho620X7ZpFBtD++8P6myXH9ln5Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0730ae2136b035c876e96d7952828664bc42fe037613d178f46255bded5dae56","last_reissued_at":"2026-07-05T09:09:30.194933Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:30.194933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Audio-Only Data for Text-Queried Target Sound Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Fran\\c{c}ois G. Germain, Gordon Wichern, Janek Ebbers, Jonathan Le Roux, Kohei Saijo, Sameer Khurana","submitted_at":"2024-09-20T01:31:29Z","abstract_excerpt":"The goal of text-queried target sound extraction (TSE) is to extract from a mixture a sound source specified with a natural-language caption. While it is preferable to have access to large-scale text-audio pairs to address a variety of text prompts, the limited number of available high-quality text-audio pairs hinders the data scaling. To this end, this work explores how to leverage audio-only data without any captions for the text-queried TSE task to potentially scale up the data amount. A straightforward way to do so is to use a joint audio-text embedding model, such as the contrastive langu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.13152","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/2409.13152/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":"2409.13152","created_at":"2026-07-05T09:09:30.194992+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.13152v1","created_at":"2026-07-05T09:09:30.194992+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.13152","created_at":"2026-07-05T09:09:30.194992+00:00"},{"alias_kind":"pith_short_12","alias_value":"A4YK4IJWWA24","created_at":"2026-07-05T09:09:30.194992+00:00"},{"alias_kind":"pith_short_16","alias_value":"A4YK4IJWWA24Q5XJ","created_at":"2026-07-05T09:09:30.194992+00:00"},{"alias_kind":"pith_short_8","alias_value":"A4YK4IJW","created_at":"2026-07-05T09:09:30.194992+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/A4YK4IJWWA24Q5XJNV4VFAUGMS","json":"https://pith.science/pith/A4YK4IJWWA24Q5XJNV4VFAUGMS.json","graph_json":"https://pith.science/api/pith-number/A4YK4IJWWA24Q5XJNV4VFAUGMS/graph.json","events_json":"https://pith.science/api/pith-number/A4YK4IJWWA24Q5XJNV4VFAUGMS/events.json","paper":"https://pith.science/paper/A4YK4IJW"},"agent_actions":{"view_html":"https://pith.science/pith/A4YK4IJWWA24Q5XJNV4VFAUGMS","download_json":"https://pith.science/pith/A4YK4IJWWA24Q5XJNV4VFAUGMS.json","view_paper":"https://pith.science/paper/A4YK4IJW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.13152&json=true","fetch_graph":"https://pith.science/api/pith-number/A4YK4IJWWA24Q5XJNV4VFAUGMS/graph.json","fetch_events":"https://pith.science/api/pith-number/A4YK4IJWWA24Q5XJNV4VFAUGMS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A4YK4IJWWA24Q5XJNV4VFAUGMS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A4YK4IJWWA24Q5XJNV4VFAUGMS/action/storage_attestation","attest_author":"https://pith.science/pith/A4YK4IJWWA24Q5XJNV4VFAUGMS/action/author_attestation","sign_citation":"https://pith.science/pith/A4YK4IJWWA24Q5XJNV4VFAUGMS/action/citation_signature","submit_replication":"https://pith.science/pith/A4YK4IJWWA24Q5XJNV4VFAUGMS/action/replication_record"}},"created_at":"2026-07-05T09:09:30.194992+00:00","updated_at":"2026-07-05T09:09:30.194992+00:00"}