{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:OGFQFWNSXEINTIWYNPHWKPJBVK","short_pith_number":"pith:OGFQFWNS","schema_version":"1.0","canonical_sha256":"718b02d9b2b910d9a2d86bcf653d21aaa5fc511f83ec78745b0e14d83ec7e024","source":{"kind":"arxiv","id":"1907.04355","version":1},"attestation_state":"computed","paper":{"title":"Transfer Learning from Audio-Visual Grounding to Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"David Harwath, James Glass, Wei-Ning Hsu","submitted_at":"2019-07-09T18:23:32Z","abstract_excerpt":"Transfer learning aims to reduce the amount of data required to excel at a new task by re-using the knowledge acquired from learning other related tasks. This paper proposes a novel transfer learning scenario, which distills robust phonetic features from grounding models that are trained to tell whether a pair of image and speech are semantically correlated, without using any textual transcripts. As semantics of speech are largely determined by its lexical content, grounding models learn to preserve phonetic information while disregarding uncorrelated factors, such as speaker and channel. To 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":"1907.04355","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-09T18:23:32Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"28ffaccdacc6e7c23bd0af4fef4e7f184fa81546a82249e075288744232d2b9c","abstract_canon_sha256":"efd33546488f6e4fa14db9040961ec61103a8d45cfe67d2180dd557275e1166f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:02.000591Z","signature_b64":"jlIIfNyDMUfGg3nLan+0p3YcQeLwFZkHPCl20L+9f4Qty3Hb/sUxyrJ7RofCnjxRv1vUvdauZb0SX0wCiLH8Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"718b02d9b2b910d9a2d86bcf653d21aaa5fc511f83ec78745b0e14d83ec7e024","last_reissued_at":"2026-05-17T23:41:01.999923Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:01.999923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transfer Learning from Audio-Visual Grounding to Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"David Harwath, James Glass, Wei-Ning Hsu","submitted_at":"2019-07-09T18:23:32Z","abstract_excerpt":"Transfer learning aims to reduce the amount of data required to excel at a new task by re-using the knowledge acquired from learning other related tasks. This paper proposes a novel transfer learning scenario, which distills robust phonetic features from grounding models that are trained to tell whether a pair of image and speech are semantically correlated, without using any textual transcripts. As semantics of speech are largely determined by its lexical content, grounding models learn to preserve phonetic information while disregarding uncorrelated factors, such as speaker and channel. To s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.04355","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":""},"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":"1907.04355","created_at":"2026-05-17T23:41:02.000024+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.04355v1","created_at":"2026-05-17T23:41:02.000024+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.04355","created_at":"2026-05-17T23:41:02.000024+00:00"},{"alias_kind":"pith_short_12","alias_value":"OGFQFWNSXEIN","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"OGFQFWNSXEINTIWY","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"OGFQFWNS","created_at":"2026-05-18T12:33:24.271573+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.04355","citing_title":"Transfer Learning from Audio-Visual Grounding to Speech Recognition","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OGFQFWNSXEINTIWYNPHWKPJBVK","json":"https://pith.science/pith/OGFQFWNSXEINTIWYNPHWKPJBVK.json","graph_json":"https://pith.science/api/pith-number/OGFQFWNSXEINTIWYNPHWKPJBVK/graph.json","events_json":"https://pith.science/api/pith-number/OGFQFWNSXEINTIWYNPHWKPJBVK/events.json","paper":"https://pith.science/paper/OGFQFWNS"},"agent_actions":{"view_html":"https://pith.science/pith/OGFQFWNSXEINTIWYNPHWKPJBVK","download_json":"https://pith.science/pith/OGFQFWNSXEINTIWYNPHWKPJBVK.json","view_paper":"https://pith.science/paper/OGFQFWNS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.04355&json=true","fetch_graph":"https://pith.science/api/pith-number/OGFQFWNSXEINTIWYNPHWKPJBVK/graph.json","fetch_events":"https://pith.science/api/pith-number/OGFQFWNSXEINTIWYNPHWKPJBVK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OGFQFWNSXEINTIWYNPHWKPJBVK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OGFQFWNSXEINTIWYNPHWKPJBVK/action/storage_attestation","attest_author":"https://pith.science/pith/OGFQFWNSXEINTIWYNPHWKPJBVK/action/author_attestation","sign_citation":"https://pith.science/pith/OGFQFWNSXEINTIWYNPHWKPJBVK/action/citation_signature","submit_replication":"https://pith.science/pith/OGFQFWNSXEINTIWYNPHWKPJBVK/action/replication_record"}},"created_at":"2026-05-17T23:41:02.000024+00:00","updated_at":"2026-05-17T23:41:02.000024+00:00"}