{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YMPO2IZFLXQZ2BACEOYM7UJOSB","short_pith_number":"pith:YMPO2IZF","schema_version":"1.0","canonical_sha256":"c31eed23255de19d040223b0cfd12e9041c10562f46755b94f1b5503e5336038","source":{"kind":"arxiv","id":"2407.04936","version":2},"attestation_state":"computed","paper":{"title":"A Reference-free Metric for Language-Queried Audio Source Separation using Contrastive Language-Audio Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Feiyang Xiao, Jian Guan, Jianyuan Sun, Kejia Zhang, Qiaoxi Zhu, Shuhan Qi, Wenbo Wang, Wenwu Wang, Xubo Liu","submitted_at":"2024-07-06T02:55:28Z","abstract_excerpt":"Language-queried audio source separation (LASS) aims to separate an audio source guided by a text query, with the signal-to-distortion ratio (SDR)-based metrics being commonly used to objectively measure the quality of the separated audio. However, the SDR-based metrics require a reference signal, which is often difficult to obtain in real-world scenarios. In addition, with the SDR-based metrics, the content information of the text query is not considered effectively in LASS. This paper introduces a reference-free evaluation metric using a contrastive language-audio pretraining (CLAP) module, "},"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":"2407.04936","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-06T02:55:28Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"216bd87ec2bfd8748b1c6648877931c4223579438ed017f68bbde0ede4b38b1d","abstract_canon_sha256":"c5e3e9ca9eaf735ee008018035b853801bc14e9ec0a877314cf1e7b3dbba713c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:52.936272Z","signature_b64":"2iW1mJd0M71lq5jWVhaNNg/Af8fJLVA5VV118O02EGof3WkwrO6LeXv6401C6J1T93GZf3mLHwZQhUdhdGbKAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c31eed23255de19d040223b0cfd12e9041c10562f46755b94f1b5503e5336038","last_reissued_at":"2026-07-05T09:56:52.935835Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:52.935835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Reference-free Metric for Language-Queried Audio Source Separation using Contrastive Language-Audio Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Feiyang Xiao, Jian Guan, Jianyuan Sun, Kejia Zhang, Qiaoxi Zhu, Shuhan Qi, Wenbo Wang, Wenwu Wang, Xubo Liu","submitted_at":"2024-07-06T02:55:28Z","abstract_excerpt":"Language-queried audio source separation (LASS) aims to separate an audio source guided by a text query, with the signal-to-distortion ratio (SDR)-based metrics being commonly used to objectively measure the quality of the separated audio. However, the SDR-based metrics require a reference signal, which is often difficult to obtain in real-world scenarios. In addition, with the SDR-based metrics, the content information of the text query is not considered effectively in LASS. This paper introduces a reference-free evaluation metric using a contrastive language-audio pretraining (CLAP) module, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04936","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/2407.04936/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":"2407.04936","created_at":"2026-07-05T09:56:52.935896+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.04936v2","created_at":"2026-07-05T09:56:52.935896+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04936","created_at":"2026-07-05T09:56:52.935896+00:00"},{"alias_kind":"pith_short_12","alias_value":"YMPO2IZFLXQZ","created_at":"2026-07-05T09:56:52.935896+00:00"},{"alias_kind":"pith_short_16","alias_value":"YMPO2IZFLXQZ2BAC","created_at":"2026-07-05T09:56:52.935896+00:00"},{"alias_kind":"pith_short_8","alias_value":"YMPO2IZF","created_at":"2026-07-05T09:56:52.935896+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/YMPO2IZFLXQZ2BACEOYM7UJOSB","json":"https://pith.science/pith/YMPO2IZFLXQZ2BACEOYM7UJOSB.json","graph_json":"https://pith.science/api/pith-number/YMPO2IZFLXQZ2BACEOYM7UJOSB/graph.json","events_json":"https://pith.science/api/pith-number/YMPO2IZFLXQZ2BACEOYM7UJOSB/events.json","paper":"https://pith.science/paper/YMPO2IZF"},"agent_actions":{"view_html":"https://pith.science/pith/YMPO2IZFLXQZ2BACEOYM7UJOSB","download_json":"https://pith.science/pith/YMPO2IZFLXQZ2BACEOYM7UJOSB.json","view_paper":"https://pith.science/paper/YMPO2IZF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.04936&json=true","fetch_graph":"https://pith.science/api/pith-number/YMPO2IZFLXQZ2BACEOYM7UJOSB/graph.json","fetch_events":"https://pith.science/api/pith-number/YMPO2IZFLXQZ2BACEOYM7UJOSB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YMPO2IZFLXQZ2BACEOYM7UJOSB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YMPO2IZFLXQZ2BACEOYM7UJOSB/action/storage_attestation","attest_author":"https://pith.science/pith/YMPO2IZFLXQZ2BACEOYM7UJOSB/action/author_attestation","sign_citation":"https://pith.science/pith/YMPO2IZFLXQZ2BACEOYM7UJOSB/action/citation_signature","submit_replication":"https://pith.science/pith/YMPO2IZFLXQZ2BACEOYM7UJOSB/action/replication_record"}},"created_at":"2026-07-05T09:56:52.935896+00:00","updated_at":"2026-07-05T09:56:52.935896+00:00"}