{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:H5KA5ZXTXSDQYP6VS5LZ4SRIOP","short_pith_number":"pith:H5KA5ZXT","schema_version":"1.0","canonical_sha256":"3f540ee6f3bc870c3fd597579e4a2873dd91b6f1ac2bd369a8c63b2e8b63f50a","source":{"kind":"arxiv","id":"2210.07189","version":3},"attestation_state":"computed","paper":{"title":"On Compressing Sequences for Self-Supervised Speech Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Hao Tang, Hsuan-Jui Chen, Hung-yi Lee, Jiatong Shi, Paola Garcia, Shinji Watanabe, Yen Meng","submitted_at":"2022-10-13T17:10:02Z","abstract_excerpt":"Compressing self-supervised models has become increasingly necessary, as self-supervised models become larger. While previous approaches have primarily focused on compressing the model size, shortening sequences is also effective in reducing the computational cost. In this work, we study fixed-length and variable-length subsampling along the time axis in self-supervised learning. We explore how individual downstream tasks are sensitive to input frame rates. Subsampling while training self-supervised models not only improves the overall performance on downstream tasks under certain frame rates,"},"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":"2210.07189","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-13T17:10:02Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"6a209b516515ed388c82ad3113c7324bf3bb61c7bfdab6c399658367036a91a3","abstract_canon_sha256":"69fac47a99ef1a879e5989cf1632f32c145d9d8d4220ee8d62e57993bc4cdabd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:10:17.177746Z","signature_b64":"lM1W0xMptrZxSos2nyA8PG0RsdTO5Ey1WkzWPbzhISXwMd4bb2XFzTcvqJZ+yIfJGN2PfIyy7ITvyE7wekRmCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f540ee6f3bc870c3fd597579e4a2873dd91b6f1ac2bd369a8c63b2e8b63f50a","last_reissued_at":"2026-07-05T05:10:17.177183Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:10:17.177183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Compressing Sequences for Self-Supervised Speech Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Hao Tang, Hsuan-Jui Chen, Hung-yi Lee, Jiatong Shi, Paola Garcia, Shinji Watanabe, Yen Meng","submitted_at":"2022-10-13T17:10:02Z","abstract_excerpt":"Compressing self-supervised models has become increasingly necessary, as self-supervised models become larger. While previous approaches have primarily focused on compressing the model size, shortening sequences is also effective in reducing the computational cost. In this work, we study fixed-length and variable-length subsampling along the time axis in self-supervised learning. We explore how individual downstream tasks are sensitive to input frame rates. Subsampling while training self-supervised models not only improves the overall performance on downstream tasks under certain frame rates,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.07189","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/2210.07189/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":"2210.07189","created_at":"2026-07-05T05:10:17.177246+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.07189v3","created_at":"2026-07-05T05:10:17.177246+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.07189","created_at":"2026-07-05T05:10:17.177246+00:00"},{"alias_kind":"pith_short_12","alias_value":"H5KA5ZXTXSDQ","created_at":"2026-07-05T05:10:17.177246+00:00"},{"alias_kind":"pith_short_16","alias_value":"H5KA5ZXTXSDQYP6V","created_at":"2026-07-05T05:10:17.177246+00:00"},{"alias_kind":"pith_short_8","alias_value":"H5KA5ZXT","created_at":"2026-07-05T05:10:17.177246+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/H5KA5ZXTXSDQYP6VS5LZ4SRIOP","json":"https://pith.science/pith/H5KA5ZXTXSDQYP6VS5LZ4SRIOP.json","graph_json":"https://pith.science/api/pith-number/H5KA5ZXTXSDQYP6VS5LZ4SRIOP/graph.json","events_json":"https://pith.science/api/pith-number/H5KA5ZXTXSDQYP6VS5LZ4SRIOP/events.json","paper":"https://pith.science/paper/H5KA5ZXT"},"agent_actions":{"view_html":"https://pith.science/pith/H5KA5ZXTXSDQYP6VS5LZ4SRIOP","download_json":"https://pith.science/pith/H5KA5ZXTXSDQYP6VS5LZ4SRIOP.json","view_paper":"https://pith.science/paper/H5KA5ZXT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.07189&json=true","fetch_graph":"https://pith.science/api/pith-number/H5KA5ZXTXSDQYP6VS5LZ4SRIOP/graph.json","fetch_events":"https://pith.science/api/pith-number/H5KA5ZXTXSDQYP6VS5LZ4SRIOP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H5KA5ZXTXSDQYP6VS5LZ4SRIOP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H5KA5ZXTXSDQYP6VS5LZ4SRIOP/action/storage_attestation","attest_author":"https://pith.science/pith/H5KA5ZXTXSDQYP6VS5LZ4SRIOP/action/author_attestation","sign_citation":"https://pith.science/pith/H5KA5ZXTXSDQYP6VS5LZ4SRIOP/action/citation_signature","submit_replication":"https://pith.science/pith/H5KA5ZXTXSDQYP6VS5LZ4SRIOP/action/replication_record"}},"created_at":"2026-07-05T05:10:17.177246+00:00","updated_at":"2026-07-05T05:10:17.177246+00:00"}