{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DCPSQGQBROKH2NVQB6VSMG5C3H","short_pith_number":"pith:DCPSQGQB","schema_version":"1.0","canonical_sha256":"189f281a018b947d36b00fab261ba2d9dbbbbf7fc97bed819e87183150375e73","source":{"kind":"arxiv","id":"2506.02057","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Speech Instruction Understanding and Disambiguation in Robotics via Speech Prosody","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.RO","authors_text":"Benedict Quartey, David Sasu, Kweku Andoh Yamoah, Natalie Schluter","submitted_at":"2025-06-01T14:06:57Z","abstract_excerpt":"Enabling robots to accurately interpret and execute spoken language instructions is essential for effective human-robot collaboration. Traditional methods rely on speech recognition to transcribe speech into text, often discarding crucial prosodic cues needed for disambiguating intent. We propose a novel approach that directly leverages speech prosody to infer and resolve instruction intent. Predicted intents are integrated into large language models via in-context learning to disambiguate and select appropriate task plans. Additionally, we present the first ambiguous speech dataset for roboti"},"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":"2506.02057","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-06-01T14:06:57Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"9f844a730e64f79e38a0d369fc43855e2a259dad280ebdce23062ea6cb9dfd53","abstract_canon_sha256":"f530948f3f84ced156aee4b4316d19dfb5b6e4a76b433be5453ecc02f96812f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:31.561279Z","signature_b64":"fYwJQJp9R+j9ebTxOECCRYRi0gYJE2v7HfmljNQPhCpiIvIlJ46j1d3DLasqLFoSahGDllT8ZThs//vR72CrAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"189f281a018b947d36b00fab261ba2d9dbbbbf7fc97bed819e87183150375e73","last_reissued_at":"2026-07-05T11:14:31.560786Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:31.560786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Speech Instruction Understanding and Disambiguation in Robotics via Speech Prosody","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.RO","authors_text":"Benedict Quartey, David Sasu, Kweku Andoh Yamoah, Natalie Schluter","submitted_at":"2025-06-01T14:06:57Z","abstract_excerpt":"Enabling robots to accurately interpret and execute spoken language instructions is essential for effective human-robot collaboration. Traditional methods rely on speech recognition to transcribe speech into text, often discarding crucial prosodic cues needed for disambiguating intent. We propose a novel approach that directly leverages speech prosody to infer and resolve instruction intent. Predicted intents are integrated into large language models via in-context learning to disambiguate and select appropriate task plans. Additionally, we present the first ambiguous speech dataset for roboti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02057","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.02057/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":"2506.02057","created_at":"2026-07-05T11:14:31.560846+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.02057v1","created_at":"2026-07-05T11:14:31.560846+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02057","created_at":"2026-07-05T11:14:31.560846+00:00"},{"alias_kind":"pith_short_12","alias_value":"DCPSQGQBROKH","created_at":"2026-07-05T11:14:31.560846+00:00"},{"alias_kind":"pith_short_16","alias_value":"DCPSQGQBROKH2NVQ","created_at":"2026-07-05T11:14:31.560846+00:00"},{"alias_kind":"pith_short_8","alias_value":"DCPSQGQB","created_at":"2026-07-05T11:14:31.560846+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02057","citing_title":"Enhancing Speech Instruction Understanding and Disambiguation in Robotics via Speech Prosody","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DCPSQGQBROKH2NVQB6VSMG5C3H","json":"https://pith.science/pith/DCPSQGQBROKH2NVQB6VSMG5C3H.json","graph_json":"https://pith.science/api/pith-number/DCPSQGQBROKH2NVQB6VSMG5C3H/graph.json","events_json":"https://pith.science/api/pith-number/DCPSQGQBROKH2NVQB6VSMG5C3H/events.json","paper":"https://pith.science/paper/DCPSQGQB"},"agent_actions":{"view_html":"https://pith.science/pith/DCPSQGQBROKH2NVQB6VSMG5C3H","download_json":"https://pith.science/pith/DCPSQGQBROKH2NVQB6VSMG5C3H.json","view_paper":"https://pith.science/paper/DCPSQGQB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.02057&json=true","fetch_graph":"https://pith.science/api/pith-number/DCPSQGQBROKH2NVQB6VSMG5C3H/graph.json","fetch_events":"https://pith.science/api/pith-number/DCPSQGQBROKH2NVQB6VSMG5C3H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DCPSQGQBROKH2NVQB6VSMG5C3H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DCPSQGQBROKH2NVQB6VSMG5C3H/action/storage_attestation","attest_author":"https://pith.science/pith/DCPSQGQBROKH2NVQB6VSMG5C3H/action/author_attestation","sign_citation":"https://pith.science/pith/DCPSQGQBROKH2NVQB6VSMG5C3H/action/citation_signature","submit_replication":"https://pith.science/pith/DCPSQGQBROKH2NVQB6VSMG5C3H/action/replication_record"}},"created_at":"2026-07-05T11:14:31.560846+00:00","updated_at":"2026-07-05T11:14:31.560846+00:00"}