{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:K24N7WMUTS5B5ZMP5XKGVGO5LF","short_pith_number":"pith:K24N7WMU","schema_version":"1.0","canonical_sha256":"56b8dfd9949cba1ee58fedd46a99dd597308fb166f19d1fc7aeb116c57f4db27","source":{"kind":"arxiv","id":"2401.04868","version":1},"attestation_state":"computed","paper":{"title":"Real-time and Continuous Turn-taking Prediction Using Voice Activity Projection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Bing'er Jiang, Erik Ekstedt, Gabriel Skantze, Koji Inoue, Tatsuya Kawahara","submitted_at":"2024-01-10T01:09:55Z","abstract_excerpt":"A demonstration of a real-time and continuous turn-taking prediction system is presented. The system is based on a voice activity projection (VAP) model, which directly maps dialogue stereo audio to future voice activities. The VAP model includes contrastive predictive coding (CPC) and self-attention transformers, followed by a cross-attention transformer. We examine the effect of the input context audio length and demonstrate that the proposed system can operate in real-time with CPU settings, with minimal performance degradation."},"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":"2401.04868","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-10T01:09:55Z","cross_cats_sorted":["cs.HC","cs.SD","eess.AS"],"title_canon_sha256":"862ec81f72ccbb58d0ad9654432e2a14b1b072bb0853d67407d4d5dce3d3dabd","abstract_canon_sha256":"8611a826fa7f30b1a5907e1c52f3ec62abe0751dc62c85f4b34c223384b5eb5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:31:59.232597Z","signature_b64":"TE6ntRU/bcjGrJcUHG2Vv1oOSjNVtucpQTqOXSqFkYBYHkmJls1ayUMToEh/BVkY6U8uTXKKowJQwkMtm0/RAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56b8dfd9949cba1ee58fedd46a99dd597308fb166f19d1fc7aeb116c57f4db27","last_reissued_at":"2026-07-05T07:31:59.232212Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:31:59.232212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Real-time and Continuous Turn-taking Prediction Using Voice Activity Projection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Bing'er Jiang, Erik Ekstedt, Gabriel Skantze, Koji Inoue, Tatsuya Kawahara","submitted_at":"2024-01-10T01:09:55Z","abstract_excerpt":"A demonstration of a real-time and continuous turn-taking prediction system is presented. The system is based on a voice activity projection (VAP) model, which directly maps dialogue stereo audio to future voice activities. The VAP model includes contrastive predictive coding (CPC) and self-attention transformers, followed by a cross-attention transformer. We examine the effect of the input context audio length and demonstrate that the proposed system can operate in real-time with CPU settings, with minimal performance degradation."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.04868","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/2401.04868/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":"2401.04868","created_at":"2026-07-05T07:31:59.232277+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.04868v1","created_at":"2026-07-05T07:31:59.232277+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.04868","created_at":"2026-07-05T07:31:59.232277+00:00"},{"alias_kind":"pith_short_12","alias_value":"K24N7WMUTS5B","created_at":"2026-07-05T07:31:59.232277+00:00"},{"alias_kind":"pith_short_16","alias_value":"K24N7WMUTS5B5ZMP","created_at":"2026-07-05T07:31:59.232277+00:00"},{"alias_kind":"pith_short_8","alias_value":"K24N7WMU","created_at":"2026-07-05T07:31:59.232277+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07294","citing_title":"Multimodal Voice Activity Projection for Turn-Taking in Social Robots with Voice-Activity-Related Pretrained Encoders","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2607.01345","citing_title":"TurnNat: Automatic Evaluation of Turn-Taking Naturalness in Dyadic Spoken Dialogue","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13450","citing_title":"Endpoint Anticipation for Low-Latency Spoken Dialogue","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09424","citing_title":"Toward Signing Activity Projection in Sign Language Interaction","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K24N7WMUTS5B5ZMP5XKGVGO5LF","json":"https://pith.science/pith/K24N7WMUTS5B5ZMP5XKGVGO5LF.json","graph_json":"https://pith.science/api/pith-number/K24N7WMUTS5B5ZMP5XKGVGO5LF/graph.json","events_json":"https://pith.science/api/pith-number/K24N7WMUTS5B5ZMP5XKGVGO5LF/events.json","paper":"https://pith.science/paper/K24N7WMU"},"agent_actions":{"view_html":"https://pith.science/pith/K24N7WMUTS5B5ZMP5XKGVGO5LF","download_json":"https://pith.science/pith/K24N7WMUTS5B5ZMP5XKGVGO5LF.json","view_paper":"https://pith.science/paper/K24N7WMU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.04868&json=true","fetch_graph":"https://pith.science/api/pith-number/K24N7WMUTS5B5ZMP5XKGVGO5LF/graph.json","fetch_events":"https://pith.science/api/pith-number/K24N7WMUTS5B5ZMP5XKGVGO5LF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K24N7WMUTS5B5ZMP5XKGVGO5LF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K24N7WMUTS5B5ZMP5XKGVGO5LF/action/storage_attestation","attest_author":"https://pith.science/pith/K24N7WMUTS5B5ZMP5XKGVGO5LF/action/author_attestation","sign_citation":"https://pith.science/pith/K24N7WMUTS5B5ZMP5XKGVGO5LF/action/citation_signature","submit_replication":"https://pith.science/pith/K24N7WMUTS5B5ZMP5XKGVGO5LF/action/replication_record"}},"created_at":"2026-07-05T07:31:59.232277+00:00","updated_at":"2026-07-05T07:31:59.232277+00:00"}