{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:I43B62TZJXZBRO7Z3L7GGTK7DF","short_pith_number":"pith:I43B62TZ","schema_version":"1.0","canonical_sha256":"47361f6a794df218bbf9dafe634d5f197d96550fad5768214679552ff0b7d905","source":{"kind":"arxiv","id":"2204.03594","version":1},"attestation_state":"computed","paper":{"title":"Heterogeneous Target Speech Separation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Aswin Subramanian, Efthymios Tzinis, Gordon Wichern, Jonathan Le Roux, Paris Smaragdis","submitted_at":"2022-04-07T17:14:20Z","abstract_excerpt":"We introduce a new paradigm for single-channel target source separation where the sources of interest can be distinguished using non-mutually exclusive concepts (e.g., loudness, gender, language, spatial location, etc). Our proposed heterogeneous separation framework can seamlessly leverage datasets with large distribution shifts and learn cross-domain representations under a variety of concepts used as conditioning. Our experiments show that training separation models with heterogeneous conditions facilitates the generalization to new concepts with unseen out-of-domain data while also perform"},"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":"2204.03594","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-04-07T17:14:20Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"65bc9178e00044c79e755d601723d867f8e264eff684d1ac7f55aca5817b36ad","abstract_canon_sha256":"9260a5b143a55f2870db8a7519a2aee96069763fa2612eb7a211762f5450afe4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:15:10.428266Z","signature_b64":"djckfYoxH5ju16sVkJ7J7PhdL1O8vmo+tK04rM3GfK+/4XZJcy94wm3ZrpsGbJJ1VLWy+0E5GUKARspXFq3/Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47361f6a794df218bbf9dafe634d5f197d96550fad5768214679552ff0b7d905","last_reissued_at":"2026-07-05T05:15:10.427776Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:15:10.427776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Heterogeneous Target Speech Separation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Aswin Subramanian, Efthymios Tzinis, Gordon Wichern, Jonathan Le Roux, Paris Smaragdis","submitted_at":"2022-04-07T17:14:20Z","abstract_excerpt":"We introduce a new paradigm for single-channel target source separation where the sources of interest can be distinguished using non-mutually exclusive concepts (e.g., loudness, gender, language, spatial location, etc). Our proposed heterogeneous separation framework can seamlessly leverage datasets with large distribution shifts and learn cross-domain representations under a variety of concepts used as conditioning. Our experiments show that training separation models with heterogeneous conditions facilitates the generalization to new concepts with unseen out-of-domain data while also perform"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.03594","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/2204.03594/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":"2204.03594","created_at":"2026-07-05T05:15:10.427835+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.03594v1","created_at":"2026-07-05T05:15:10.427835+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.03594","created_at":"2026-07-05T05:15:10.427835+00:00"},{"alias_kind":"pith_short_12","alias_value":"I43B62TZJXZB","created_at":"2026-07-05T05:15:10.427835+00:00"},{"alias_kind":"pith_short_16","alias_value":"I43B62TZJXZBRO7Z","created_at":"2026-07-05T05:15:10.427835+00:00"},{"alias_kind":"pith_short_8","alias_value":"I43B62TZ","created_at":"2026-07-05T05:15:10.427835+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/I43B62TZJXZBRO7Z3L7GGTK7DF","json":"https://pith.science/pith/I43B62TZJXZBRO7Z3L7GGTK7DF.json","graph_json":"https://pith.science/api/pith-number/I43B62TZJXZBRO7Z3L7GGTK7DF/graph.json","events_json":"https://pith.science/api/pith-number/I43B62TZJXZBRO7Z3L7GGTK7DF/events.json","paper":"https://pith.science/paper/I43B62TZ"},"agent_actions":{"view_html":"https://pith.science/pith/I43B62TZJXZBRO7Z3L7GGTK7DF","download_json":"https://pith.science/pith/I43B62TZJXZBRO7Z3L7GGTK7DF.json","view_paper":"https://pith.science/paper/I43B62TZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.03594&json=true","fetch_graph":"https://pith.science/api/pith-number/I43B62TZJXZBRO7Z3L7GGTK7DF/graph.json","fetch_events":"https://pith.science/api/pith-number/I43B62TZJXZBRO7Z3L7GGTK7DF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I43B62TZJXZBRO7Z3L7GGTK7DF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I43B62TZJXZBRO7Z3L7GGTK7DF/action/storage_attestation","attest_author":"https://pith.science/pith/I43B62TZJXZBRO7Z3L7GGTK7DF/action/author_attestation","sign_citation":"https://pith.science/pith/I43B62TZJXZBRO7Z3L7GGTK7DF/action/citation_signature","submit_replication":"https://pith.science/pith/I43B62TZJXZBRO7Z3L7GGTK7DF/action/replication_record"}},"created_at":"2026-07-05T05:15:10.427835+00:00","updated_at":"2026-07-05T05:15:10.427835+00:00"}