{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:UG4MUYRJHC65GFTDFD4AIUR73X","short_pith_number":"pith:UG4MUYRJ","schema_version":"1.0","canonical_sha256":"a1b8ca622938bdd3166328f804523fddd782b7068b395d85fdb03c33830f5216","source":{"kind":"arxiv","id":"2211.05172","version":2},"attestation_state":"computed","paper":{"title":"Speech separation with large-scale self-supervised learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Jian Wu, Jinyu Li, Naoyuki Kanda, Sefik Emre Eskimez, Sunit Sivasankaran, Takuya Yoshioka, Xiaofei Wang, Yu Wu, Zhuo Chen","submitted_at":"2022-11-09T20:00:21Z","abstract_excerpt":"Self-supervised learning (SSL) methods such as WavLM have shown promising speech separation (SS) results in small-scale simulation-based experiments. In this work, we extend the exploration of the SSL-based SS by massively scaling up both the pre-training data (more than 300K hours) and fine-tuning data (10K hours). We also investigate various techniques to efficiently integrate the pre-trained model with the SS network under a limited computation budget, including a low frame rate SSL model training setup and a fine-tuning scheme using only the part of the pre-trained model. Compared with a s"},"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":"2211.05172","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-09T20:00:21Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"579548b85b2fbd745077a5f9be8fe664cc77935fb5206861fae7fd2de932ae3b","abstract_canon_sha256":"b48b439fbe80c9dd568d66cca180e5c2142ad2dfa9931747ac1468de3aea878f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:19:37.392757Z","signature_b64":"YwpudixbSk6G06L91PtkO+xVSW3OKUyyIOgnCXYmP/MB/zHBBVzRX0KrkyNEcYmAxJcHo3Ce2PYKU/Nl/CRqBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1b8ca622938bdd3166328f804523fddd782b7068b395d85fdb03c33830f5216","last_reissued_at":"2026-07-05T05:19:37.392265Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:19:37.392265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Speech separation with large-scale self-supervised learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Jian Wu, Jinyu Li, Naoyuki Kanda, Sefik Emre Eskimez, Sunit Sivasankaran, Takuya Yoshioka, Xiaofei Wang, Yu Wu, Zhuo Chen","submitted_at":"2022-11-09T20:00:21Z","abstract_excerpt":"Self-supervised learning (SSL) methods such as WavLM have shown promising speech separation (SS) results in small-scale simulation-based experiments. In this work, we extend the exploration of the SSL-based SS by massively scaling up both the pre-training data (more than 300K hours) and fine-tuning data (10K hours). We also investigate various techniques to efficiently integrate the pre-trained model with the SS network under a limited computation budget, including a low frame rate SSL model training setup and a fine-tuning scheme using only the part of the pre-trained model. Compared with a s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.05172","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/2211.05172/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":"2211.05172","created_at":"2026-07-05T05:19:37.392338+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.05172v2","created_at":"2026-07-05T05:19:37.392338+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.05172","created_at":"2026-07-05T05:19:37.392338+00:00"},{"alias_kind":"pith_short_12","alias_value":"UG4MUYRJHC65","created_at":"2026-07-05T05:19:37.392338+00:00"},{"alias_kind":"pith_short_16","alias_value":"UG4MUYRJHC65GFTD","created_at":"2026-07-05T05:19:37.392338+00:00"},{"alias_kind":"pith_short_8","alias_value":"UG4MUYRJ","created_at":"2026-07-05T05:19:37.392338+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/UG4MUYRJHC65GFTDFD4AIUR73X","json":"https://pith.science/pith/UG4MUYRJHC65GFTDFD4AIUR73X.json","graph_json":"https://pith.science/api/pith-number/UG4MUYRJHC65GFTDFD4AIUR73X/graph.json","events_json":"https://pith.science/api/pith-number/UG4MUYRJHC65GFTDFD4AIUR73X/events.json","paper":"https://pith.science/paper/UG4MUYRJ"},"agent_actions":{"view_html":"https://pith.science/pith/UG4MUYRJHC65GFTDFD4AIUR73X","download_json":"https://pith.science/pith/UG4MUYRJHC65GFTDFD4AIUR73X.json","view_paper":"https://pith.science/paper/UG4MUYRJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.05172&json=true","fetch_graph":"https://pith.science/api/pith-number/UG4MUYRJHC65GFTDFD4AIUR73X/graph.json","fetch_events":"https://pith.science/api/pith-number/UG4MUYRJHC65GFTDFD4AIUR73X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UG4MUYRJHC65GFTDFD4AIUR73X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UG4MUYRJHC65GFTDFD4AIUR73X/action/storage_attestation","attest_author":"https://pith.science/pith/UG4MUYRJHC65GFTDFD4AIUR73X/action/author_attestation","sign_citation":"https://pith.science/pith/UG4MUYRJHC65GFTDFD4AIUR73X/action/citation_signature","submit_replication":"https://pith.science/pith/UG4MUYRJHC65GFTDFD4AIUR73X/action/replication_record"}},"created_at":"2026-07-05T05:19:37.392338+00:00","updated_at":"2026-07-05T05:19:37.392338+00:00"}