{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:7J2SDZ6UYTLKRIPCULJQJ2OE4U","short_pith_number":"pith:7J2SDZ6U","schema_version":"1.0","canonical_sha256":"fa7521e7d4c4d6a8a1e2a2d304e9c4e512a05a00e659a2e7472d78ab16d92314","source":{"kind":"arxiv","id":"1707.08435","version":5},"attestation_state":"computed","paper":{"title":"SPEECH-COCO: 600k Visually Grounded Spoken Captions Aligned to MSCOCO Data Set","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Laurent Besacier, Olivier Rosec, William Havard","submitted_at":"2017-07-26T13:40:21Z","abstract_excerpt":"This paper presents an augmentation of MSCOCO dataset where speech is added to image and text. Speech captions are generated using text-to-speech (TTS) synthesis resulting in 616,767 spoken captions (more than 600h) paired with images. Disfluencies and speed perturbation are added to the signal in order to sound more natural. Each speech signal (WAV) is paired with a JSON file containing exact timecode for each word/syllable/phoneme in the spoken caption. Such a corpus could be used for Language and Vision (LaVi) tasks including speech input or output instead of text. Investigating multimodal "},"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":"1707.08435","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2017-07-26T13:40:21Z","cross_cats_sorted":[],"title_canon_sha256":"935e3585be3a92ae257de118e1358a9b740ceb78325804fa97d11047277de200","abstract_canon_sha256":"7ae6653e3d948bd96ed407ec8121bef42b1dc55b601372bf5f7b405b52b91d4f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:53:35.165386Z","signature_b64":"yV4oOzSq43hRPRyykdRRiLafSEIdmARBSEt6TnJnOv7R1kUmCRbq95RPWBuSwKCfPf9e2pHjrKQ8bUh6/3+9Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa7521e7d4c4d6a8a1e2a2d304e9c4e512a05a00e659a2e7472d78ab16d92314","last_reissued_at":"2026-07-05T01:53:35.164967Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:53:35.164967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPEECH-COCO: 600k Visually Grounded Spoken Captions Aligned to MSCOCO Data Set","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Laurent Besacier, Olivier Rosec, William Havard","submitted_at":"2017-07-26T13:40:21Z","abstract_excerpt":"This paper presents an augmentation of MSCOCO dataset where speech is added to image and text. Speech captions are generated using text-to-speech (TTS) synthesis resulting in 616,767 spoken captions (more than 600h) paired with images. Disfluencies and speed perturbation are added to the signal in order to sound more natural. Each speech signal (WAV) is paired with a JSON file containing exact timecode for each word/syllable/phoneme in the spoken caption. Such a corpus could be used for Language and Vision (LaVi) tasks including speech input or output instead of text. Investigating multimodal "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.08435","kind":"arxiv","version":5},"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/1707.08435/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":"1707.08435","created_at":"2026-07-05T01:53:35.165025+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.08435v5","created_at":"2026-07-05T01:53:35.165025+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.08435","created_at":"2026-07-05T01:53:35.165025+00:00"},{"alias_kind":"pith_short_12","alias_value":"7J2SDZ6UYTLK","created_at":"2026-07-05T01:53:35.165025+00:00"},{"alias_kind":"pith_short_16","alias_value":"7J2SDZ6UYTLKRIPC","created_at":"2026-07-05T01:53:35.165025+00:00"},{"alias_kind":"pith_short_8","alias_value":"7J2SDZ6U","created_at":"2026-07-05T01:53:35.165025+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.23321","citing_title":"MMEB-V3: Measuring the Performance Gaps of Omni-Modality Embedding Models","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7J2SDZ6UYTLKRIPCULJQJ2OE4U","json":"https://pith.science/pith/7J2SDZ6UYTLKRIPCULJQJ2OE4U.json","graph_json":"https://pith.science/api/pith-number/7J2SDZ6UYTLKRIPCULJQJ2OE4U/graph.json","events_json":"https://pith.science/api/pith-number/7J2SDZ6UYTLKRIPCULJQJ2OE4U/events.json","paper":"https://pith.science/paper/7J2SDZ6U"},"agent_actions":{"view_html":"https://pith.science/pith/7J2SDZ6UYTLKRIPCULJQJ2OE4U","download_json":"https://pith.science/pith/7J2SDZ6UYTLKRIPCULJQJ2OE4U.json","view_paper":"https://pith.science/paper/7J2SDZ6U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.08435&json=true","fetch_graph":"https://pith.science/api/pith-number/7J2SDZ6UYTLKRIPCULJQJ2OE4U/graph.json","fetch_events":"https://pith.science/api/pith-number/7J2SDZ6UYTLKRIPCULJQJ2OE4U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7J2SDZ6UYTLKRIPCULJQJ2OE4U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7J2SDZ6UYTLKRIPCULJQJ2OE4U/action/storage_attestation","attest_author":"https://pith.science/pith/7J2SDZ6UYTLKRIPCULJQJ2OE4U/action/author_attestation","sign_citation":"https://pith.science/pith/7J2SDZ6UYTLKRIPCULJQJ2OE4U/action/citation_signature","submit_replication":"https://pith.science/pith/7J2SDZ6UYTLKRIPCULJQJ2OE4U/action/replication_record"}},"created_at":"2026-07-05T01:53:35.165025+00:00","updated_at":"2026-07-05T01:53:35.165025+00:00"}