{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FTDZQ4G7T6FEBTOQWOEJU2OIAR","short_pith_number":"pith:FTDZQ4G7","schema_version":"1.0","canonical_sha256":"2cc79870df9f8a40cdd0b3889a69c8044a67e30ecca2a9b99e26d78584e0ee95","source":{"kind":"arxiv","id":"2406.07867","version":2},"attestation_state":"computed","paper":{"title":"Let's Go Real Talk: Spoken Dialogue Model for Face-to-Face Conversation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CV","authors_text":"Chae Won Kim, Hyeongseop Rha, Jeong Hun Yeo, Joanna Hong, Minsu Kim, Se Jin Park, Yong Man Ro","submitted_at":"2024-06-12T04:48:36Z","abstract_excerpt":"In this paper, we introduce a novel Face-to-Face spoken dialogue model. It processes audio-visual speech from user input and generates audio-visual speech as the response, marking the initial step towards creating an avatar chatbot system without relying on intermediate text. To this end, we newly introduce MultiDialog, the first large-scale multimodal (i.e., audio and visual) spoken dialogue corpus containing 340 hours of approximately 9,000 dialogues, recorded based on the open domain dialogue dataset, TopicalChat. The MultiDialog contains parallel audio-visual recordings of conversation par"},"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":"2406.07867","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-12T04:48:36Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"e8b8e1df291feca5c64d817cf64cec9bc11257beb5b90757ad26264e180fbba2","abstract_canon_sha256":"5caad778cd0fa933d0bd102f961d9ce9ba5f374902378e4d0301da459bfb4ec1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:51:18.239005Z","signature_b64":"a/bbKGpFU20iKebZ47XRiJia7HqBlhqJhpgL/HKEBEpttgq01G4L6YErcBX5uGXZmIhHD8VGt4Rs++0U3jsLBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cc79870df9f8a40cdd0b3889a69c8044a67e30ecca2a9b99e26d78584e0ee95","last_reissued_at":"2026-07-05T08:51:18.238506Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:51:18.238506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Let's Go Real Talk: Spoken Dialogue Model for Face-to-Face Conversation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CV","authors_text":"Chae Won Kim, Hyeongseop Rha, Jeong Hun Yeo, Joanna Hong, Minsu Kim, Se Jin Park, Yong Man Ro","submitted_at":"2024-06-12T04:48:36Z","abstract_excerpt":"In this paper, we introduce a novel Face-to-Face spoken dialogue model. It processes audio-visual speech from user input and generates audio-visual speech as the response, marking the initial step towards creating an avatar chatbot system without relying on intermediate text. To this end, we newly introduce MultiDialog, the first large-scale multimodal (i.e., audio and visual) spoken dialogue corpus containing 340 hours of approximately 9,000 dialogues, recorded based on the open domain dialogue dataset, TopicalChat. The MultiDialog contains parallel audio-visual recordings of conversation par"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07867","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/2406.07867/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":"2406.07867","created_at":"2026-07-05T08:51:18.238567+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.07867v2","created_at":"2026-07-05T08:51:18.238567+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07867","created_at":"2026-07-05T08:51:18.238567+00:00"},{"alias_kind":"pith_short_12","alias_value":"FTDZQ4G7T6FE","created_at":"2026-07-05T08:51:18.238567+00:00"},{"alias_kind":"pith_short_16","alias_value":"FTDZQ4G7T6FEBTOQ","created_at":"2026-07-05T08:51:18.238567+00:00"},{"alias_kind":"pith_short_8","alias_value":"FTDZQ4G7","created_at":"2026-07-05T08:51:18.238567+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.00472","citing_title":"ARIG: Autoregressive Interactive Head Generation for Real-time Conversations","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FTDZQ4G7T6FEBTOQWOEJU2OIAR","json":"https://pith.science/pith/FTDZQ4G7T6FEBTOQWOEJU2OIAR.json","graph_json":"https://pith.science/api/pith-number/FTDZQ4G7T6FEBTOQWOEJU2OIAR/graph.json","events_json":"https://pith.science/api/pith-number/FTDZQ4G7T6FEBTOQWOEJU2OIAR/events.json","paper":"https://pith.science/paper/FTDZQ4G7"},"agent_actions":{"view_html":"https://pith.science/pith/FTDZQ4G7T6FEBTOQWOEJU2OIAR","download_json":"https://pith.science/pith/FTDZQ4G7T6FEBTOQWOEJU2OIAR.json","view_paper":"https://pith.science/paper/FTDZQ4G7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.07867&json=true","fetch_graph":"https://pith.science/api/pith-number/FTDZQ4G7T6FEBTOQWOEJU2OIAR/graph.json","fetch_events":"https://pith.science/api/pith-number/FTDZQ4G7T6FEBTOQWOEJU2OIAR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FTDZQ4G7T6FEBTOQWOEJU2OIAR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FTDZQ4G7T6FEBTOQWOEJU2OIAR/action/storage_attestation","attest_author":"https://pith.science/pith/FTDZQ4G7T6FEBTOQWOEJU2OIAR/action/author_attestation","sign_citation":"https://pith.science/pith/FTDZQ4G7T6FEBTOQWOEJU2OIAR/action/citation_signature","submit_replication":"https://pith.science/pith/FTDZQ4G7T6FEBTOQWOEJU2OIAR/action/replication_record"}},"created_at":"2026-07-05T08:51:18.238567+00:00","updated_at":"2026-07-05T08:51:18.238567+00:00"}