{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:UEV6TR5UCVIIH7STUZKOSO4XQR","short_pith_number":"pith:UEV6TR5U","schema_version":"1.0","canonical_sha256":"a12be9c7b4155083fe53a654e93b9784793236ba36e865b763ffacb43d788cba","source":{"kind":"arxiv","id":"2211.07321","version":3},"attestation_state":"computed","paper":{"title":"MT4SSL: Boosting Self-Supervised Speech Representation Learning by Integrating Multiple Targets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Changli Tang, Xie Chen, Yujin Wang, Zhisheng Zheng, Ziyang Ma","submitted_at":"2022-11-14T13:00:47Z","abstract_excerpt":"In this paper, we provide a new perspective on self-supervised speech models from how the training targets are obtained. We generalize the targets extractor into Offline Targets Extractor (Off-TE) and Online Targets Extractor (On-TE). Based on this, we propose a new multi-tasking learning framework for self-supervised learning, MT4SSL, which stands for Boosting Self-Supervised Speech Representation Learning by Integrating Multiple Targets. MT4SSL uses the K-means algorithm as an Off-TE and a teacher network without gradients as an On-TE, respectively. Our model outperforms previous SSL methods"},"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":"2211.07321","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-14T13:00:47Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"bd61a7395f6a45e6ec7116ffe513dc5b3bd1200bce8604cb2c96975ceda405b3","abstract_canon_sha256":"9252593e24ad895cb0a92bb71c632e69c309878c4244e9e54c8410dbb6d7e72b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:15:43.811268Z","signature_b64":"sUZSM5RRVYodIZxv1hs/IRld4sm9bhXhfJf8Bqw4biDhO4Y9mkNyx/KPeeReMjCHvFWKasNY4lxXsKeKYUHbCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a12be9c7b4155083fe53a654e93b9784793236ba36e865b763ffacb43d788cba","last_reissued_at":"2026-07-05T06:15:43.810726Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:15:43.810726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MT4SSL: Boosting Self-Supervised Speech Representation Learning by Integrating Multiple Targets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Changli Tang, Xie Chen, Yujin Wang, Zhisheng Zheng, Ziyang Ma","submitted_at":"2022-11-14T13:00:47Z","abstract_excerpt":"In this paper, we provide a new perspective on self-supervised speech models from how the training targets are obtained. We generalize the targets extractor into Offline Targets Extractor (Off-TE) and Online Targets Extractor (On-TE). Based on this, we propose a new multi-tasking learning framework for self-supervised learning, MT4SSL, which stands for Boosting Self-Supervised Speech Representation Learning by Integrating Multiple Targets. MT4SSL uses the K-means algorithm as an Off-TE and a teacher network without gradients as an On-TE, respectively. Our model outperforms previous SSL methods"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.07321","kind":"arxiv","version":3},"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/2211.07321/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":"2211.07321","created_at":"2026-07-05T06:15:43.810790+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.07321v3","created_at":"2026-07-05T06:15:43.810790+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.07321","created_at":"2026-07-05T06:15:43.810790+00:00"},{"alias_kind":"pith_short_12","alias_value":"UEV6TR5UCVII","created_at":"2026-07-05T06:15:43.810790+00:00"},{"alias_kind":"pith_short_16","alias_value":"UEV6TR5UCVIIH7ST","created_at":"2026-07-05T06:15:43.810790+00:00"},{"alias_kind":"pith_short_8","alias_value":"UEV6TR5U","created_at":"2026-07-05T06:15:43.810790+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/UEV6TR5UCVIIH7STUZKOSO4XQR","json":"https://pith.science/pith/UEV6TR5UCVIIH7STUZKOSO4XQR.json","graph_json":"https://pith.science/api/pith-number/UEV6TR5UCVIIH7STUZKOSO4XQR/graph.json","events_json":"https://pith.science/api/pith-number/UEV6TR5UCVIIH7STUZKOSO4XQR/events.json","paper":"https://pith.science/paper/UEV6TR5U"},"agent_actions":{"view_html":"https://pith.science/pith/UEV6TR5UCVIIH7STUZKOSO4XQR","download_json":"https://pith.science/pith/UEV6TR5UCVIIH7STUZKOSO4XQR.json","view_paper":"https://pith.science/paper/UEV6TR5U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.07321&json=true","fetch_graph":"https://pith.science/api/pith-number/UEV6TR5UCVIIH7STUZKOSO4XQR/graph.json","fetch_events":"https://pith.science/api/pith-number/UEV6TR5UCVIIH7STUZKOSO4XQR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UEV6TR5UCVIIH7STUZKOSO4XQR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UEV6TR5UCVIIH7STUZKOSO4XQR/action/storage_attestation","attest_author":"https://pith.science/pith/UEV6TR5UCVIIH7STUZKOSO4XQR/action/author_attestation","sign_citation":"https://pith.science/pith/UEV6TR5UCVIIH7STUZKOSO4XQR/action/citation_signature","submit_replication":"https://pith.science/pith/UEV6TR5UCVIIH7STUZKOSO4XQR/action/replication_record"}},"created_at":"2026-07-05T06:15:43.810790+00:00","updated_at":"2026-07-05T06:15:43.810790+00:00"}