{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:A6K4VWWSH3ZVUSKVBPI7RHQ5K2","short_pith_number":"pith:A6K4VWWS","schema_version":"1.0","canonical_sha256":"0795cadad23ef35a49550bd1f89e1d56aab2c981fd50411ede840450f0551a69","source":{"kind":"arxiv","id":"2402.05819","version":1},"attestation_state":"computed","paper":{"title":"Integrating Self-supervised Speech Model with Pseudo Word-level Targets from Visually-grounded Speech Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"eess.AS","authors_text":"David Harwath, Hsuan-Fu Wang, Hung-Chieh Fang, Hung-yi Lee, Layne Berry, Nai-Xuan Ye, Puyuan Peng, Yi-Jen Shih","submitted_at":"2024-02-08T16:55:21Z","abstract_excerpt":"Recent advances in self-supervised speech models have shown significant improvement in many downstream tasks. However, these models predominantly centered on frame-level training objectives, which can fall short in spoken language understanding tasks that require semantic comprehension. Existing works often rely on additional speech-text data as intermediate targets, which is costly in the real-world setting. To address this challenge, we propose Pseudo-Word HuBERT (PW-HuBERT), a framework that integrates pseudo word-level targets into the training process, where the targets are derived from a"},"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":"2402.05819","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-02-08T16:55:21Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"4630330bf55425a994ccaf0138a6c7c3aca8829127477f9ff48f002f4689ffd9","abstract_canon_sha256":"00caddd7147009ff951525cfcdc18e35555d785e5a16ad472a85d3b7658b83a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:43:03.847587Z","signature_b64":"Pr6HeK8b2NsRtk9Aj2nd4YPp/StCK5J6CChU8rydu0ikLfTlaDaY9DRhEzJMpkNQUEvs4EKOAHROZC6NXTcUBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0795cadad23ef35a49550bd1f89e1d56aab2c981fd50411ede840450f0551a69","last_reissued_at":"2026-07-05T07:43:03.847152Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:43:03.847152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Integrating Self-supervised Speech Model with Pseudo Word-level Targets from Visually-grounded Speech Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"eess.AS","authors_text":"David Harwath, Hsuan-Fu Wang, Hung-Chieh Fang, Hung-yi Lee, Layne Berry, Nai-Xuan Ye, Puyuan Peng, Yi-Jen Shih","submitted_at":"2024-02-08T16:55:21Z","abstract_excerpt":"Recent advances in self-supervised speech models have shown significant improvement in many downstream tasks. However, these models predominantly centered on frame-level training objectives, which can fall short in spoken language understanding tasks that require semantic comprehension. Existing works often rely on additional speech-text data as intermediate targets, which is costly in the real-world setting. To address this challenge, we propose Pseudo-Word HuBERT (PW-HuBERT), a framework that integrates pseudo word-level targets into the training process, where the targets are derived from a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05819","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/2402.05819/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":"2402.05819","created_at":"2026-07-05T07:43:03.847201+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.05819v1","created_at":"2026-07-05T07:43:03.847201+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05819","created_at":"2026-07-05T07:43:03.847201+00:00"},{"alias_kind":"pith_short_12","alias_value":"A6K4VWWSH3ZV","created_at":"2026-07-05T07:43:03.847201+00:00"},{"alias_kind":"pith_short_16","alias_value":"A6K4VWWSH3ZVUSKV","created_at":"2026-07-05T07:43:03.847201+00:00"},{"alias_kind":"pith_short_8","alias_value":"A6K4VWWS","created_at":"2026-07-05T07:43:03.847201+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/A6K4VWWSH3ZVUSKVBPI7RHQ5K2","json":"https://pith.science/pith/A6K4VWWSH3ZVUSKVBPI7RHQ5K2.json","graph_json":"https://pith.science/api/pith-number/A6K4VWWSH3ZVUSKVBPI7RHQ5K2/graph.json","events_json":"https://pith.science/api/pith-number/A6K4VWWSH3ZVUSKVBPI7RHQ5K2/events.json","paper":"https://pith.science/paper/A6K4VWWS"},"agent_actions":{"view_html":"https://pith.science/pith/A6K4VWWSH3ZVUSKVBPI7RHQ5K2","download_json":"https://pith.science/pith/A6K4VWWSH3ZVUSKVBPI7RHQ5K2.json","view_paper":"https://pith.science/paper/A6K4VWWS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.05819&json=true","fetch_graph":"https://pith.science/api/pith-number/A6K4VWWSH3ZVUSKVBPI7RHQ5K2/graph.json","fetch_events":"https://pith.science/api/pith-number/A6K4VWWSH3ZVUSKVBPI7RHQ5K2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A6K4VWWSH3ZVUSKVBPI7RHQ5K2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A6K4VWWSH3ZVUSKVBPI7RHQ5K2/action/storage_attestation","attest_author":"https://pith.science/pith/A6K4VWWSH3ZVUSKVBPI7RHQ5K2/action/author_attestation","sign_citation":"https://pith.science/pith/A6K4VWWSH3ZVUSKVBPI7RHQ5K2/action/citation_signature","submit_replication":"https://pith.science/pith/A6K4VWWSH3ZVUSKVBPI7RHQ5K2/action/replication_record"}},"created_at":"2026-07-05T07:43:03.847201+00:00","updated_at":"2026-07-05T07:43:03.847201+00:00"}