{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DUW6C7QZ3MJRH3CEN4FVBJZFSG","short_pith_number":"pith:DUW6C7QZ","schema_version":"1.0","canonical_sha256":"1d2de17e19db1313ec446f0b50a72591885d123327bbc9b60fe624b2f68f040c","source":{"kind":"arxiv","id":"2203.15147","version":1},"attestation_state":"computed","paper":{"title":"Separate What You Describe: Language-Queried Audio Source Separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.SD","eess.SP"],"primary_cat":"eess.AS","authors_text":"Haohe Liu, Jinzheng Zhao, Mark D. Plumbley, Qiuqiang Kong, Qiushi Huang, Wenwu Wang, Xinhao Mei, Xubo Liu","submitted_at":"2022-03-28T23:47:57Z","abstract_excerpt":"In this paper, we introduce the task of language-queried audio source separation (LASS), which aims to separate a target source from an audio mixture based on a natural language query of the target source (e.g., \"a man tells a joke followed by people laughing\"). A unique challenge in LASS is associated with the complexity of natural language description and its relation with the audio sources. To address this issue, we proposed LASS-Net, an end-to-end neural network that is learned to jointly process acoustic and linguistic information, and separate the target source that is consistent with th"},"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":"2203.15147","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-03-28T23:47:57Z","cross_cats_sorted":["cs.AI","cs.CL","cs.SD","eess.SP"],"title_canon_sha256":"93628fed4a951490e5dc210055c45af8fa437d1565d5dcf8b7ad2572dd32498b","abstract_canon_sha256":"3cd64ceb209b934361d1330b25da2429e2dcec564e5574585edb8aff683f7f78"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:09:22.178902Z","signature_b64":"GeTG07VVUCiOSydAsuBxH+DDjpwZkRKbOkBXBcR/sx9/E5G7NK756vny5kfCHjF366HVLRyPJzlCvA3wV5XfAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d2de17e19db1313ec446f0b50a72591885d123327bbc9b60fe624b2f68f040c","last_reissued_at":"2026-07-05T04:09:22.178495Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:09:22.178495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Separate What You Describe: Language-Queried Audio Source Separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.SD","eess.SP"],"primary_cat":"eess.AS","authors_text":"Haohe Liu, Jinzheng Zhao, Mark D. Plumbley, Qiuqiang Kong, Qiushi Huang, Wenwu Wang, Xinhao Mei, Xubo Liu","submitted_at":"2022-03-28T23:47:57Z","abstract_excerpt":"In this paper, we introduce the task of language-queried audio source separation (LASS), which aims to separate a target source from an audio mixture based on a natural language query of the target source (e.g., \"a man tells a joke followed by people laughing\"). A unique challenge in LASS is associated with the complexity of natural language description and its relation with the audio sources. To address this issue, we proposed LASS-Net, an end-to-end neural network that is learned to jointly process acoustic and linguistic information, and separate the target source that is consistent with th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.15147","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/2203.15147/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":"2203.15147","created_at":"2026-07-05T04:09:22.178553+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.15147v1","created_at":"2026-07-05T04:09:22.178553+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.15147","created_at":"2026-07-05T04:09:22.178553+00:00"},{"alias_kind":"pith_short_12","alias_value":"DUW6C7QZ3MJR","created_at":"2026-07-05T04:09:22.178553+00:00"},{"alias_kind":"pith_short_16","alias_value":"DUW6C7QZ3MJRH3CE","created_at":"2026-07-05T04:09:22.178553+00:00"},{"alias_kind":"pith_short_8","alias_value":"DUW6C7QZ","created_at":"2026-07-05T04:09:22.178553+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/DUW6C7QZ3MJRH3CEN4FVBJZFSG","json":"https://pith.science/pith/DUW6C7QZ3MJRH3CEN4FVBJZFSG.json","graph_json":"https://pith.science/api/pith-number/DUW6C7QZ3MJRH3CEN4FVBJZFSG/graph.json","events_json":"https://pith.science/api/pith-number/DUW6C7QZ3MJRH3CEN4FVBJZFSG/events.json","paper":"https://pith.science/paper/DUW6C7QZ"},"agent_actions":{"view_html":"https://pith.science/pith/DUW6C7QZ3MJRH3CEN4FVBJZFSG","download_json":"https://pith.science/pith/DUW6C7QZ3MJRH3CEN4FVBJZFSG.json","view_paper":"https://pith.science/paper/DUW6C7QZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.15147&json=true","fetch_graph":"https://pith.science/api/pith-number/DUW6C7QZ3MJRH3CEN4FVBJZFSG/graph.json","fetch_events":"https://pith.science/api/pith-number/DUW6C7QZ3MJRH3CEN4FVBJZFSG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DUW6C7QZ3MJRH3CEN4FVBJZFSG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DUW6C7QZ3MJRH3CEN4FVBJZFSG/action/storage_attestation","attest_author":"https://pith.science/pith/DUW6C7QZ3MJRH3CEN4FVBJZFSG/action/author_attestation","sign_citation":"https://pith.science/pith/DUW6C7QZ3MJRH3CEN4FVBJZFSG/action/citation_signature","submit_replication":"https://pith.science/pith/DUW6C7QZ3MJRH3CEN4FVBJZFSG/action/replication_record"}},"created_at":"2026-07-05T04:09:22.178553+00:00","updated_at":"2026-07-05T04:09:22.178553+00:00"}