{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2MJUNPPIOSFLP2TUI73SVHVPH4","short_pith_number":"pith:2MJUNPPI","schema_version":"1.0","canonical_sha256":"d31346bde8748ab7ea7447f72a9eaf3f32792dfb662ef5afe5ffac00bb840223","source":{"kind":"arxiv","id":"2202.03543","version":2},"attestation_state":"computed","paper":{"title":"Self-Supervised Representation Learning for Speech Using Visual Grounding and Masked Language Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"David Harwath, Puyuan Peng","submitted_at":"2022-02-07T22:09:54Z","abstract_excerpt":"In this paper, we describe our submissions to the ZeroSpeech 2021 Challenge and SUPERB benchmark. Our submissions are based on the recently proposed FaST-VGS model, which is a Transformer-based model that learns to associate raw speech waveforms with semantically related images, all without the use of any transcriptions of the speech. Additionally, we introduce a novel extension of this model, FaST-VGS+, which is learned in a multi-task fashion with a masked language modeling objective in addition to the visual grounding objective. On ZeroSpeech 2021, we show that our models perform competitiv"},"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":"2202.03543","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-02-07T22:09:54Z","cross_cats_sorted":["cs.CL","cs.CV","cs.LG","cs.SD"],"title_canon_sha256":"36463a86653d1efab4d88bc42ef674625f9c98fe95f5ebe89f747203a9c109d5","abstract_canon_sha256":"d47c753725a3a7a1edec119320043f9108f3919287207c4ec08990aae3f2dafe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:01:34.388830Z","signature_b64":"oYnZ5QLmqIzeFhDdRhBGAbU2ECoS//X/7nQPz/oX02qIa2hbMJg+VOy4eQ6q/xybS8XkVZmP1xv1netyFHHMBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d31346bde8748ab7ea7447f72a9eaf3f32792dfb662ef5afe5ffac00bb840223","last_reissued_at":"2026-07-05T04:01:34.388356Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:01:34.388356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Supervised Representation Learning for Speech Using Visual Grounding and Masked Language Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"David Harwath, Puyuan Peng","submitted_at":"2022-02-07T22:09:54Z","abstract_excerpt":"In this paper, we describe our submissions to the ZeroSpeech 2021 Challenge and SUPERB benchmark. Our submissions are based on the recently proposed FaST-VGS model, which is a Transformer-based model that learns to associate raw speech waveforms with semantically related images, all without the use of any transcriptions of the speech. Additionally, we introduce a novel extension of this model, FaST-VGS+, which is learned in a multi-task fashion with a masked language modeling objective in addition to the visual grounding objective. On ZeroSpeech 2021, we show that our models perform competitiv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.03543","kind":"arxiv","version":2},"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/2202.03543/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":"2202.03543","created_at":"2026-07-05T04:01:34.388416+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.03543v2","created_at":"2026-07-05T04:01:34.388416+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.03543","created_at":"2026-07-05T04:01:34.388416+00:00"},{"alias_kind":"pith_short_12","alias_value":"2MJUNPPIOSFL","created_at":"2026-07-05T04:01:34.388416+00:00"},{"alias_kind":"pith_short_16","alias_value":"2MJUNPPIOSFLP2TU","created_at":"2026-07-05T04:01:34.388416+00:00"},{"alias_kind":"pith_short_8","alias_value":"2MJUNPPI","created_at":"2026-07-05T04:01:34.388416+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/2MJUNPPIOSFLP2TUI73SVHVPH4","json":"https://pith.science/pith/2MJUNPPIOSFLP2TUI73SVHVPH4.json","graph_json":"https://pith.science/api/pith-number/2MJUNPPIOSFLP2TUI73SVHVPH4/graph.json","events_json":"https://pith.science/api/pith-number/2MJUNPPIOSFLP2TUI73SVHVPH4/events.json","paper":"https://pith.science/paper/2MJUNPPI"},"agent_actions":{"view_html":"https://pith.science/pith/2MJUNPPIOSFLP2TUI73SVHVPH4","download_json":"https://pith.science/pith/2MJUNPPIOSFLP2TUI73SVHVPH4.json","view_paper":"https://pith.science/paper/2MJUNPPI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.03543&json=true","fetch_graph":"https://pith.science/api/pith-number/2MJUNPPIOSFLP2TUI73SVHVPH4/graph.json","fetch_events":"https://pith.science/api/pith-number/2MJUNPPIOSFLP2TUI73SVHVPH4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2MJUNPPIOSFLP2TUI73SVHVPH4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2MJUNPPIOSFLP2TUI73SVHVPH4/action/storage_attestation","attest_author":"https://pith.science/pith/2MJUNPPIOSFLP2TUI73SVHVPH4/action/author_attestation","sign_citation":"https://pith.science/pith/2MJUNPPIOSFLP2TUI73SVHVPH4/action/citation_signature","submit_replication":"https://pith.science/pith/2MJUNPPIOSFLP2TUI73SVHVPH4/action/replication_record"}},"created_at":"2026-07-05T04:01:34.388416+00:00","updated_at":"2026-07-05T04:01:34.388416+00:00"}