{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:T4KDRPFFRIWOXQYQJ7RBHO2ZHJ","short_pith_number":"pith:T4KDRPFF","schema_version":"1.0","canonical_sha256":"9f1438bca58a2cebc3104fe213bb593a778531da3660e310a6fc4cb6cf6bc7d2","source":{"kind":"arxiv","id":"2503.06241","version":2},"attestation_state":"computed","paper":{"title":"A Noise-Robust Turn-Taking System for Real-World Dialogue Robots: A Field Experiment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"cs.RO","authors_text":"Jun Baba, Katsuya Hyodo, Koji Inoue, Tatsuya Kawahara, Yoshiki Ohira, Yuki Okafuji","submitted_at":"2025-03-08T14:53:20Z","abstract_excerpt":"Turn-taking is a crucial aspect of human-robot interaction, directly influencing conversational fluidity and user engagement. While previous research has explored turn-taking models in controlled environments, their robustness in real-world settings remains underexplored. In this study, we propose a noise-robust voice activity projection (VAP) model, based on a Transformer architecture, to enhance real-time turn-taking in dialogue robots. To evaluate the effectiveness of the proposed system, we conducted a field experiment in a shopping mall, comparing the VAP system with a conventional cloud-"},"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":"2503.06241","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-03-08T14:53:20Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"ac2a5b41b1686188e279d663d58dcc78afb8ce1017c1bb7cc6cff8c7e8c53309","abstract_canon_sha256":"1cf1ea5ef5fb33dba05fe4fc77d8cb208028188721ca870eba7b0ec6d20fa5f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:29.342749Z","signature_b64":"+7SPvGiKfPKnGz0IhaZsD2/tJ23gixuPJpwZHf9gnLpknmfiaaDbnr3m0JTkjQ4wW8RWYy2K6MQxbGgU4DAJBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f1438bca58a2cebc3104fe213bb593a778531da3660e310a6fc4cb6cf6bc7d2","last_reissued_at":"2026-07-05T11:36:29.342155Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:29.342155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Noise-Robust Turn-Taking System for Real-World Dialogue Robots: A Field Experiment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"cs.RO","authors_text":"Jun Baba, Katsuya Hyodo, Koji Inoue, Tatsuya Kawahara, Yoshiki Ohira, Yuki Okafuji","submitted_at":"2025-03-08T14:53:20Z","abstract_excerpt":"Turn-taking is a crucial aspect of human-robot interaction, directly influencing conversational fluidity and user engagement. While previous research has explored turn-taking models in controlled environments, their robustness in real-world settings remains underexplored. In this study, we propose a noise-robust voice activity projection (VAP) model, based on a Transformer architecture, to enhance real-time turn-taking in dialogue robots. To evaluate the effectiveness of the proposed system, we conducted a field experiment in a shopping mall, comparing the VAP system with a conventional cloud-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.06241","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2503.06241/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":"2503.06241","created_at":"2026-07-05T11:36:29.342214+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.06241v2","created_at":"2026-07-05T11:36:29.342214+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.06241","created_at":"2026-07-05T11:36:29.342214+00:00"},{"alias_kind":"pith_short_12","alias_value":"T4KDRPFFRIWO","created_at":"2026-07-05T11:36:29.342214+00:00"},{"alias_kind":"pith_short_16","alias_value":"T4KDRPFFRIWOXQYQ","created_at":"2026-07-05T11:36:29.342214+00:00"},{"alias_kind":"pith_short_8","alias_value":"T4KDRPFF","created_at":"2026-07-05T11:36:29.342214+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09424","citing_title":"Toward Signing Activity Projection in Sign Language Interaction","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T4KDRPFFRIWOXQYQJ7RBHO2ZHJ","json":"https://pith.science/pith/T4KDRPFFRIWOXQYQJ7RBHO2ZHJ.json","graph_json":"https://pith.science/api/pith-number/T4KDRPFFRIWOXQYQJ7RBHO2ZHJ/graph.json","events_json":"https://pith.science/api/pith-number/T4KDRPFFRIWOXQYQJ7RBHO2ZHJ/events.json","paper":"https://pith.science/paper/T4KDRPFF"},"agent_actions":{"view_html":"https://pith.science/pith/T4KDRPFFRIWOXQYQJ7RBHO2ZHJ","download_json":"https://pith.science/pith/T4KDRPFFRIWOXQYQJ7RBHO2ZHJ.json","view_paper":"https://pith.science/paper/T4KDRPFF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.06241&json=true","fetch_graph":"https://pith.science/api/pith-number/T4KDRPFFRIWOXQYQJ7RBHO2ZHJ/graph.json","fetch_events":"https://pith.science/api/pith-number/T4KDRPFFRIWOXQYQJ7RBHO2ZHJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T4KDRPFFRIWOXQYQJ7RBHO2ZHJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T4KDRPFFRIWOXQYQJ7RBHO2ZHJ/action/storage_attestation","attest_author":"https://pith.science/pith/T4KDRPFFRIWOXQYQJ7RBHO2ZHJ/action/author_attestation","sign_citation":"https://pith.science/pith/T4KDRPFFRIWOXQYQJ7RBHO2ZHJ/action/citation_signature","submit_replication":"https://pith.science/pith/T4KDRPFFRIWOXQYQJ7RBHO2ZHJ/action/replication_record"}},"created_at":"2026-07-05T11:36:29.342214+00:00","updated_at":"2026-07-05T11:36:29.342214+00:00"}