{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4FSYZFKWAWW7GXGWVYTDXWMLZS","short_pith_number":"pith:4FSYZFKW","canonical_record":{"source":{"id":"2402.13199","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-02-17T13:45:00Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"23de10ef9c42a95c954a4d59cb383e1d7801f0550b1259afcc323a415fdacffa","abstract_canon_sha256":"abeb794944569ca3a64ad11716f275b3e95da3e92c49d3272a6f864ba5385285"},"schema_version":"1.0"},"canonical_sha256":"e1658c955605adf35cd6ae263bd98bccb89b4f69b966b40521b98d8ac0863342","source":{"kind":"arxiv","id":"2402.13199","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13199","created_at":"2026-07-05T07:47:21Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13199v1","created_at":"2026-07-05T07:47:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13199","created_at":"2026-07-05T07:47:21Z"},{"alias_kind":"pith_short_12","alias_value":"4FSYZFKWAWW7","created_at":"2026-07-05T07:47:21Z"},{"alias_kind":"pith_short_16","alias_value":"4FSYZFKWAWW7GXGW","created_at":"2026-07-05T07:47:21Z"},{"alias_kind":"pith_short_8","alias_value":"4FSYZFKW","created_at":"2026-07-05T07:47:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4FSYZFKWAWW7GXGWVYTDXWMLZS","target":"record","payload":{"canonical_record":{"source":{"id":"2402.13199","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-02-17T13:45:00Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"23de10ef9c42a95c954a4d59cb383e1d7801f0550b1259afcc323a415fdacffa","abstract_canon_sha256":"abeb794944569ca3a64ad11716f275b3e95da3e92c49d3272a6f864ba5385285"},"schema_version":"1.0"},"canonical_sha256":"e1658c955605adf35cd6ae263bd98bccb89b4f69b966b40521b98d8ac0863342","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:47:21.985153Z","signature_b64":"2PmVy+HAg2e8y4pPDP8oPxOX5dyq5P+3Zumymk2TwEal0Z2ZCHWpnUDC5NqgYHxtJbXef5ojP5nTQNxVa7AcBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1658c955605adf35cd6ae263bd98bccb89b4f69b966b40521b98d8ac0863342","last_reissued_at":"2026-07-05T07:47:21.984712Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:47:21.984712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.13199","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:47:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8NFoPP8PSEIMLnVii+Z5Bhso38qXHu8N7pHvamO5aVh/10zoL3Aa62QsyHJ0IyLjVgD6pQuoOFG/1KYJCZF/CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T19:10:15.918276Z"},"content_sha256":"947921a42f67e09038a3cdccc8c8692db8e533c2b845e88519f0ec27040e4767","schema_version":"1.0","event_id":"sha256:947921a42f67e09038a3cdccc8c8692db8e533c2b845e88519f0ec27040e4767"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4FSYZFKWAWW7GXGWVYTDXWMLZS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Target Speech Extraction with Pre-trained Self-supervised Learning Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Jan Cernocky, Junyi Peng, Marc Delcroix, Oldrich Plchot, Shoko Araki, Tsubasa Ochiai","submitted_at":"2024-02-17T13:45:00Z","abstract_excerpt":"Pre-trained self-supervised learning (SSL) models have achieved remarkable success in various speech tasks. However, their potential in target speech extraction (TSE) has not been fully exploited. TSE aims to extract the speech of a target speaker in a mixture guided by enrollment utterances. We exploit pre-trained SSL models for two purposes within a TSE framework, i.e., to process the input mixture and to derive speaker embeddings from the enrollment. In this paper, we focus on how to effectively use SSL models for TSE. We first introduce a novel TSE downstream task following the SUPERB prin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13199","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/2402.13199/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:47:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qtxz2EfIKj6LJz0XofRp0moEjArq/sCjUOu2QKWIap8dLZiJTwak97dOdBLsrij1jNDYTULFWHGCrRScJWGvCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T19:10:15.918667Z"},"content_sha256":"2a6de790f0144032d5e11a004e8a3f03fc6b3120397f85c19d65e6bb78d81dab","schema_version":"1.0","event_id":"sha256:2a6de790f0144032d5e11a004e8a3f03fc6b3120397f85c19d65e6bb78d81dab"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4FSYZFKWAWW7GXGWVYTDXWMLZS/bundle.json","state_url":"https://pith.science/pith/4FSYZFKWAWW7GXGWVYTDXWMLZS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4FSYZFKWAWW7GXGWVYTDXWMLZS/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-08T19:10:15Z","links":{"resolver":"https://pith.science/pith/4FSYZFKWAWW7GXGWVYTDXWMLZS","bundle":"https://pith.science/pith/4FSYZFKWAWW7GXGWVYTDXWMLZS/bundle.json","state":"https://pith.science/pith/4FSYZFKWAWW7GXGWVYTDXWMLZS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4FSYZFKWAWW7GXGWVYTDXWMLZS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4FSYZFKWAWW7GXGWVYTDXWMLZS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"abeb794944569ca3a64ad11716f275b3e95da3e92c49d3272a6f864ba5385285","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-02-17T13:45:00Z","title_canon_sha256":"23de10ef9c42a95c954a4d59cb383e1d7801f0550b1259afcc323a415fdacffa"},"schema_version":"1.0","source":{"id":"2402.13199","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13199","created_at":"2026-07-05T07:47:21Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13199v1","created_at":"2026-07-05T07:47:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13199","created_at":"2026-07-05T07:47:21Z"},{"alias_kind":"pith_short_12","alias_value":"4FSYZFKWAWW7","created_at":"2026-07-05T07:47:21Z"},{"alias_kind":"pith_short_16","alias_value":"4FSYZFKWAWW7GXGW","created_at":"2026-07-05T07:47:21Z"},{"alias_kind":"pith_short_8","alias_value":"4FSYZFKW","created_at":"2026-07-05T07:47:21Z"}],"graph_snapshots":[{"event_id":"sha256:2a6de790f0144032d5e11a004e8a3f03fc6b3120397f85c19d65e6bb78d81dab","target":"graph","created_at":"2026-07-05T07:47:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2402.13199/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained self-supervised learning (SSL) models have achieved remarkable success in various speech tasks. However, their potential in target speech extraction (TSE) has not been fully exploited. TSE aims to extract the speech of a target speaker in a mixture guided by enrollment utterances. We exploit pre-trained SSL models for two purposes within a TSE framework, i.e., to process the input mixture and to derive speaker embeddings from the enrollment. In this paper, we focus on how to effectively use SSL models for TSE. We first introduce a novel TSE downstream task following the SUPERB prin","authors_text":"Jan Cernocky, Junyi Peng, Marc Delcroix, Oldrich Plchot, Shoko Araki, Tsubasa Ochiai","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-02-17T13:45:00Z","title":"Target Speech Extraction with Pre-trained Self-supervised Learning Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13199","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:947921a42f67e09038a3cdccc8c8692db8e533c2b845e88519f0ec27040e4767","target":"record","created_at":"2026-07-05T07:47:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"abeb794944569ca3a64ad11716f275b3e95da3e92c49d3272a6f864ba5385285","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-02-17T13:45:00Z","title_canon_sha256":"23de10ef9c42a95c954a4d59cb383e1d7801f0550b1259afcc323a415fdacffa"},"schema_version":"1.0","source":{"id":"2402.13199","kind":"arxiv","version":1}},"canonical_sha256":"e1658c955605adf35cd6ae263bd98bccb89b4f69b966b40521b98d8ac0863342","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e1658c955605adf35cd6ae263bd98bccb89b4f69b966b40521b98d8ac0863342","first_computed_at":"2026-07-05T07:47:21.984712Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:47:21.984712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2PmVy+HAg2e8y4pPDP8oPxOX5dyq5P+3Zumymk2TwEal0Z2ZCHWpnUDC5NqgYHxtJbXef5ojP5nTQNxVa7AcBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:47:21.985153Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.13199","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:947921a42f67e09038a3cdccc8c8692db8e533c2b845e88519f0ec27040e4767","sha256:2a6de790f0144032d5e11a004e8a3f03fc6b3120397f85c19d65e6bb78d81dab"],"state_sha256":"7b4b1bc9d545f58b9fa4f6caf7cbae0deb0518b9d97cd4b09d80dd0ca6136bcd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"scYHIlkEGtzRArXG5grYiCH0sRe+4Zma/Vsu69xaknXRshFG0MTgi1TTW7X6+wZzTYvckMVC29E6/3hi0t/8Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T19:10:15.920852Z","bundle_sha256":"5da92b3caa259b417b95928a24055e80a6305c4cd01e2c931224b3222b9fc418"}}