{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:GYSGDGDWLN6KAR44WHKETROVKW","short_pith_number":"pith:GYSGDGDW","schema_version":"1.0","canonical_sha256":"36246198765b7ca0479cb1d449c5d5559577ef0afbd94efaeac86f7df1005afd","source":{"kind":"arxiv","id":"1704.06913","version":2},"attestation_state":"computed","paper":{"title":"Learning weakly supervised multimodal phoneme embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Emmanuel Dupoux, Ewan Dunbar, Neil Zeghidour, Rahma Chaabouni","submitted_at":"2017-04-23T11:27:53Z","abstract_excerpt":"Recent works have explored deep architectures for learning multimodal speech representation (e.g. audio and images, articulation and audio) in a supervised way. Here we investigate the role of combining different speech modalities, i.e. audio and visual information representing the lips movements, in a weakly supervised way using Siamese networks and lexical same-different side information. In particular, we ask whether one modality can benefit from the other to provide a richer representation for phone recognition in a weakly supervised setting. We introduce mono-task and multi-task methods f"},"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":"1704.06913","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2017-04-23T11:27:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ed9b0ba8c14d3aa27032ab04049ddccd3b8083ef80b485d16eb46715230a6cf6","abstract_canon_sha256":"f283cce6bd7ac618c931bccb8386be2ca98fa290c44530399580ae2302c82ccc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:32:36.255139Z","signature_b64":"APIH8dqPcRTak7R0C5+TMA4iGnbqSqBV+OYP9JYDorx5474hROk75Pd3mRB8lzCcSbrhicfhuXIQzD/0SlgdBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36246198765b7ca0479cb1d449c5d5559577ef0afbd94efaeac86f7df1005afd","last_reissued_at":"2026-05-18T00:32:36.254443Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:32:36.254443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning weakly supervised multimodal phoneme embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Emmanuel Dupoux, Ewan Dunbar, Neil Zeghidour, Rahma Chaabouni","submitted_at":"2017-04-23T11:27:53Z","abstract_excerpt":"Recent works have explored deep architectures for learning multimodal speech representation (e.g. audio and images, articulation and audio) in a supervised way. Here we investigate the role of combining different speech modalities, i.e. audio and visual information representing the lips movements, in a weakly supervised way using Siamese networks and lexical same-different side information. In particular, we ask whether one modality can benefit from the other to provide a richer representation for phone recognition in a weakly supervised setting. We introduce mono-task and multi-task methods f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.06913","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":""},"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":"1704.06913","created_at":"2026-05-18T00:32:36.254572+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.06913v2","created_at":"2026-05-18T00:32:36.254572+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.06913","created_at":"2026-05-18T00:32:36.254572+00:00"},{"alias_kind":"pith_short_12","alias_value":"GYSGDGDWLN6K","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"GYSGDGDWLN6KAR44","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"GYSGDGDW","created_at":"2026-05-18T12:31:18.294218+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/GYSGDGDWLN6KAR44WHKETROVKW","json":"https://pith.science/pith/GYSGDGDWLN6KAR44WHKETROVKW.json","graph_json":"https://pith.science/api/pith-number/GYSGDGDWLN6KAR44WHKETROVKW/graph.json","events_json":"https://pith.science/api/pith-number/GYSGDGDWLN6KAR44WHKETROVKW/events.json","paper":"https://pith.science/paper/GYSGDGDW"},"agent_actions":{"view_html":"https://pith.science/pith/GYSGDGDWLN6KAR44WHKETROVKW","download_json":"https://pith.science/pith/GYSGDGDWLN6KAR44WHKETROVKW.json","view_paper":"https://pith.science/paper/GYSGDGDW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.06913&json=true","fetch_graph":"https://pith.science/api/pith-number/GYSGDGDWLN6KAR44WHKETROVKW/graph.json","fetch_events":"https://pith.science/api/pith-number/GYSGDGDWLN6KAR44WHKETROVKW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GYSGDGDWLN6KAR44WHKETROVKW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GYSGDGDWLN6KAR44WHKETROVKW/action/storage_attestation","attest_author":"https://pith.science/pith/GYSGDGDWLN6KAR44WHKETROVKW/action/author_attestation","sign_citation":"https://pith.science/pith/GYSGDGDWLN6KAR44WHKETROVKW/action/citation_signature","submit_replication":"https://pith.science/pith/GYSGDGDWLN6KAR44WHKETROVKW/action/replication_record"}},"created_at":"2026-05-18T00:32:36.254572+00:00","updated_at":"2026-05-18T00:32:36.254572+00:00"}