{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:6WLX3AAAMXUTAEAL4VOXEAX4TR","short_pith_number":"pith:6WLX3AAA","schema_version":"1.0","canonical_sha256":"f5977d800065e930100be55d7202fc9c7cc1af01aa183948957a436b4f9bc52c","source":{"kind":"arxiv","id":"1907.01195","version":1},"attestation_state":"computed","paper":{"title":"Kite: Automatic speech recognition for unmanned aerial vehicles","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dan Oneata, Horia Cucu","submitted_at":"2019-07-02T06:50:24Z","abstract_excerpt":"This paper addresses the problem of building a speech recognition system attuned to the control of unmanned aerial vehicles (UAVs). Even though UAVs are becoming widespread, the task of creating voice interfaces for them is largely unaddressed. To this end, we introduce a multi-modal evaluation dataset for UAV control, consisting of spoken commands and associated images, which represent the visual context of what the UAV \"sees\" when the pilot utters the command. We provide baseline results and address two research directions: (i) how robust the language models are, given an incomplete list of "},"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":"1907.01195","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2019-07-02T06:50:24Z","cross_cats_sorted":["cs.CV","eess.AS"],"title_canon_sha256":"de777ac93eb5546c113732f9a3df5e1c1e3f7435183379fccce7751be6fbe28c","abstract_canon_sha256":"b8bf2e4cfe4a63610e4afedb829c9726d2f0d0add5a0031cf22ab060a901a9e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:40.989544Z","signature_b64":"7SQIrEQa5z6jnN5HhhwskyOzQDx6pOrEVqW8o1kCg4xtYZdzDp8CSRAi9IU8l9gFnE3BUxPWHOMYDeqQXuNQDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5977d800065e930100be55d7202fc9c7cc1af01aa183948957a436b4f9bc52c","last_reissued_at":"2026-05-17T23:41:40.989059Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:40.989059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Kite: Automatic speech recognition for unmanned aerial vehicles","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dan Oneata, Horia Cucu","submitted_at":"2019-07-02T06:50:24Z","abstract_excerpt":"This paper addresses the problem of building a speech recognition system attuned to the control of unmanned aerial vehicles (UAVs). Even though UAVs are becoming widespread, the task of creating voice interfaces for them is largely unaddressed. To this end, we introduce a multi-modal evaluation dataset for UAV control, consisting of spoken commands and associated images, which represent the visual context of what the UAV \"sees\" when the pilot utters the command. We provide baseline results and address two research directions: (i) how robust the language models are, given an incomplete list of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.01195","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":"1907.01195","created_at":"2026-05-17T23:41:40.989139+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.01195v1","created_at":"2026-05-17T23:41:40.989139+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.01195","created_at":"2026-05-17T23:41:40.989139+00:00"},{"alias_kind":"pith_short_12","alias_value":"6WLX3AAAMXUT","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"6WLX3AAAMXUTAEAL","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"6WLX3AAA","created_at":"2026-05-18T12:33:10.108867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.01195","citing_title":"Kite: Automatic speech recognition for unmanned aerial vehicles","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6WLX3AAAMXUTAEAL4VOXEAX4TR","json":"https://pith.science/pith/6WLX3AAAMXUTAEAL4VOXEAX4TR.json","graph_json":"https://pith.science/api/pith-number/6WLX3AAAMXUTAEAL4VOXEAX4TR/graph.json","events_json":"https://pith.science/api/pith-number/6WLX3AAAMXUTAEAL4VOXEAX4TR/events.json","paper":"https://pith.science/paper/6WLX3AAA"},"agent_actions":{"view_html":"https://pith.science/pith/6WLX3AAAMXUTAEAL4VOXEAX4TR","download_json":"https://pith.science/pith/6WLX3AAAMXUTAEAL4VOXEAX4TR.json","view_paper":"https://pith.science/paper/6WLX3AAA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.01195&json=true","fetch_graph":"https://pith.science/api/pith-number/6WLX3AAAMXUTAEAL4VOXEAX4TR/graph.json","fetch_events":"https://pith.science/api/pith-number/6WLX3AAAMXUTAEAL4VOXEAX4TR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6WLX3AAAMXUTAEAL4VOXEAX4TR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6WLX3AAAMXUTAEAL4VOXEAX4TR/action/storage_attestation","attest_author":"https://pith.science/pith/6WLX3AAAMXUTAEAL4VOXEAX4TR/action/author_attestation","sign_citation":"https://pith.science/pith/6WLX3AAAMXUTAEAL4VOXEAX4TR/action/citation_signature","submit_replication":"https://pith.science/pith/6WLX3AAAMXUTAEAL4VOXEAX4TR/action/replication_record"}},"created_at":"2026-05-17T23:41:40.989139+00:00","updated_at":"2026-05-17T23:41:40.989139+00:00"}