{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:DSQBL6R762L5MW3RGW6GISQZNP","short_pith_number":"pith:DSQBL6R7","schema_version":"1.0","canonical_sha256":"1ca015fa3ff697d65b7135bc644a196be3fcfcf5cddf62fefbd327bf415ca60b","source":{"kind":"arxiv","id":"1710.01949","version":2},"attestation_state":"computed","paper":{"title":"Semantic speech retrieval with a visually grounded model of untranscribed speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","eess.AS"],"primary_cat":"cs.CL","authors_text":"Gregory Shakhnarovich, Herman Kamper, Karen Livescu","submitted_at":"2017-10-05T10:24:46Z","abstract_excerpt":"There is growing interest in models that can learn from unlabelled speech paired with visual context. This setting is relevant for low-resource speech processing, robotics, and human language acquisition research. Here we study how a visually grounded speech model, trained on images of scenes paired with spoken captions, captures aspects of semantics. We use an external image tagger to generate soft text labels from images, which serve as targets for a neural model that maps untranscribed speech to (semantic) keyword labels. We introduce a newly collected data set of human semantic relevance j"},"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":"1710.01949","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-05T10:24:46Z","cross_cats_sorted":["cs.CV","eess.AS"],"title_canon_sha256":"527c32e05da8d274ad55ecc0c2f19d091f450e9363709defbca381d01ee9d1ec","abstract_canon_sha256":"f2bfc32ff533f6a523c068ba20fb49a3a5fab66971948ef797139225107735d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:47.418916Z","signature_b64":"NsPPdP9DrQ3UPn8Ks9aQ020PLudUs6OCZLGNfBrZ1wLx1EOA4Qi9CGcsHQAEiuO4XH0ToDoD0V/R7rABA4tjCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ca015fa3ff697d65b7135bc644a196be3fcfcf5cddf62fefbd327bf415ca60b","last_reissued_at":"2026-05-18T00:01:47.418166Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:47.418166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semantic speech retrieval with a visually grounded model of untranscribed speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","eess.AS"],"primary_cat":"cs.CL","authors_text":"Gregory Shakhnarovich, Herman Kamper, Karen Livescu","submitted_at":"2017-10-05T10:24:46Z","abstract_excerpt":"There is growing interest in models that can learn from unlabelled speech paired with visual context. This setting is relevant for low-resource speech processing, robotics, and human language acquisition research. Here we study how a visually grounded speech model, trained on images of scenes paired with spoken captions, captures aspects of semantics. We use an external image tagger to generate soft text labels from images, which serve as targets for a neural model that maps untranscribed speech to (semantic) keyword labels. We introduce a newly collected data set of human semantic relevance j"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.01949","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":"1710.01949","created_at":"2026-05-18T00:01:47.418289+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.01949v2","created_at":"2026-05-18T00:01:47.418289+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.01949","created_at":"2026-05-18T00:01:47.418289+00:00"},{"alias_kind":"pith_short_12","alias_value":"DSQBL6R762L5","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_16","alias_value":"DSQBL6R762L5MW3R","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_8","alias_value":"DSQBL6R7","created_at":"2026-05-18T12:31:12.930513+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/DSQBL6R762L5MW3RGW6GISQZNP","json":"https://pith.science/pith/DSQBL6R762L5MW3RGW6GISQZNP.json","graph_json":"https://pith.science/api/pith-number/DSQBL6R762L5MW3RGW6GISQZNP/graph.json","events_json":"https://pith.science/api/pith-number/DSQBL6R762L5MW3RGW6GISQZNP/events.json","paper":"https://pith.science/paper/DSQBL6R7"},"agent_actions":{"view_html":"https://pith.science/pith/DSQBL6R762L5MW3RGW6GISQZNP","download_json":"https://pith.science/pith/DSQBL6R762L5MW3RGW6GISQZNP.json","view_paper":"https://pith.science/paper/DSQBL6R7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.01949&json=true","fetch_graph":"https://pith.science/api/pith-number/DSQBL6R762L5MW3RGW6GISQZNP/graph.json","fetch_events":"https://pith.science/api/pith-number/DSQBL6R762L5MW3RGW6GISQZNP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DSQBL6R762L5MW3RGW6GISQZNP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DSQBL6R762L5MW3RGW6GISQZNP/action/storage_attestation","attest_author":"https://pith.science/pith/DSQBL6R762L5MW3RGW6GISQZNP/action/author_attestation","sign_citation":"https://pith.science/pith/DSQBL6R762L5MW3RGW6GISQZNP/action/citation_signature","submit_replication":"https://pith.science/pith/DSQBL6R762L5MW3RGW6GISQZNP/action/replication_record"}},"created_at":"2026-05-18T00:01:47.418289+00:00","updated_at":"2026-05-18T00:01:47.418289+00:00"}