{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ERVHZUGMKVSM7T3FREDV6N33V5","short_pith_number":"pith:ERVHZUGM","schema_version":"1.0","canonical_sha256":"246a7cd0cc5564cfcf6589075f377baf77b6d099b034bbcca4173e847266eb9f","source":{"kind":"arxiv","id":"2409.00387","version":1},"attestation_state":"computed","paper":{"title":"Progressive Residual Extraction based Pre-training for Speech Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Jianwu Dang, Jin Li, Longbiao Wang, Meng Ge, Nyima Tashi, Rui Cao, Tianrui Wang, Xiaobao Wang, Xie Chen, Yuguang Wang, Ziyang Ma","submitted_at":"2024-08-31T08:33:13Z","abstract_excerpt":"Self-supervised learning (SSL) has garnered significant attention in speech processing, excelling in linguistic tasks such as speech recognition. However, jointly improving the performance of pre-trained models on various downstream tasks, each requiring different speech information, poses significant challenges. To this purpose, we propose a progressive residual extraction based self-supervised learning method, named ProgRE. Specifically, we introduce two lightweight and specialized task modules into an encoder-style SSL backbone to enhance its ability to extract pitch variation and speaker i"},"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":"2409.00387","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-08-31T08:33:13Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"31c4f8822ca2b0dcbf85f57c588c77cd50ac45bde81d67541b47f1d024cc7162","abstract_canon_sha256":"efadf10ef3e72ee1d7a4ce6f8c24421d4444be1409416b866951371b6002b805"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:01:46.760898Z","signature_b64":"mwRUtoUHNEYBrQgXFcebeCI8DnYxmQa7R0uBjSnE2SRvLOZrzq8NBu47BzmhSFmvb3+9me2BKb6Q8ZYYEMRdCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"246a7cd0cc5564cfcf6589075f377baf77b6d099b034bbcca4173e847266eb9f","last_reissued_at":"2026-07-05T09:01:46.760442Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:01:46.760442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Progressive Residual Extraction based Pre-training for Speech Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Jianwu Dang, Jin Li, Longbiao Wang, Meng Ge, Nyima Tashi, Rui Cao, Tianrui Wang, Xiaobao Wang, Xie Chen, Yuguang Wang, Ziyang Ma","submitted_at":"2024-08-31T08:33:13Z","abstract_excerpt":"Self-supervised learning (SSL) has garnered significant attention in speech processing, excelling in linguistic tasks such as speech recognition. However, jointly improving the performance of pre-trained models on various downstream tasks, each requiring different speech information, poses significant challenges. To this purpose, we propose a progressive residual extraction based self-supervised learning method, named ProgRE. Specifically, we introduce two lightweight and specialized task modules into an encoder-style SSL backbone to enhance its ability to extract pitch variation and speaker i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.00387","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/2409.00387/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":"2409.00387","created_at":"2026-07-05T09:01:46.760505+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.00387v1","created_at":"2026-07-05T09:01:46.760505+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.00387","created_at":"2026-07-05T09:01:46.760505+00:00"},{"alias_kind":"pith_short_12","alias_value":"ERVHZUGMKVSM","created_at":"2026-07-05T09:01:46.760505+00:00"},{"alias_kind":"pith_short_16","alias_value":"ERVHZUGMKVSM7T3F","created_at":"2026-07-05T09:01:46.760505+00:00"},{"alias_kind":"pith_short_8","alias_value":"ERVHZUGM","created_at":"2026-07-05T09:01:46.760505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.02666","citing_title":"ASDA: Audio Spectrogram Differential Attention Mechanism for Self-Supervised Representation Learning","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ERVHZUGMKVSM7T3FREDV6N33V5","json":"https://pith.science/pith/ERVHZUGMKVSM7T3FREDV6N33V5.json","graph_json":"https://pith.science/api/pith-number/ERVHZUGMKVSM7T3FREDV6N33V5/graph.json","events_json":"https://pith.science/api/pith-number/ERVHZUGMKVSM7T3FREDV6N33V5/events.json","paper":"https://pith.science/paper/ERVHZUGM"},"agent_actions":{"view_html":"https://pith.science/pith/ERVHZUGMKVSM7T3FREDV6N33V5","download_json":"https://pith.science/pith/ERVHZUGMKVSM7T3FREDV6N33V5.json","view_paper":"https://pith.science/paper/ERVHZUGM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.00387&json=true","fetch_graph":"https://pith.science/api/pith-number/ERVHZUGMKVSM7T3FREDV6N33V5/graph.json","fetch_events":"https://pith.science/api/pith-number/ERVHZUGMKVSM7T3FREDV6N33V5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ERVHZUGMKVSM7T3FREDV6N33V5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ERVHZUGMKVSM7T3FREDV6N33V5/action/storage_attestation","attest_author":"https://pith.science/pith/ERVHZUGMKVSM7T3FREDV6N33V5/action/author_attestation","sign_citation":"https://pith.science/pith/ERVHZUGMKVSM7T3FREDV6N33V5/action/citation_signature","submit_replication":"https://pith.science/pith/ERVHZUGMKVSM7T3FREDV6N33V5/action/replication_record"}},"created_at":"2026-07-05T09:01:46.760505+00:00","updated_at":"2026-07-05T09:01:46.760505+00:00"}