{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FBBOTMNDIAZRFTIXH7HVC2RCOM","short_pith_number":"pith:FBBOTMND","schema_version":"1.0","canonical_sha256":"2842e9b1a3403312cd173fcf516a22732a5ac82c0e938fd6b6cbaa3574da17ff","source":{"kind":"arxiv","id":"2305.11094","version":1},"attestation_state":"computed","paper":{"title":"QPGesture: Quantization-Based and Phase-Guided Motion Matching for Natural Speech-Driven Gesture Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.HC","authors_text":"Haolin Zhuang, Lei Hao, Minglei Li, Sicheng Yang, Weihong Bao, Zhensong Zhang, Zhiyong Wu","submitted_at":"2023-05-18T16:31:25Z","abstract_excerpt":"Speech-driven gesture generation is highly challenging due to the random jitters of human motion. In addition, there is an inherent asynchronous relationship between human speech and gestures. To tackle these challenges, we introduce a novel quantization-based and phase-guided motion-matching framework. Specifically, we first present a gesture VQ-VAE module to learn a codebook to summarize meaningful gesture units. With each code representing a unique gesture, random jittering problems are alleviated effectively. We then use Levenshtein distance to align diverse gestures with different speech."},"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":"2305.11094","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2023-05-18T16:31:25Z","cross_cats_sorted":["cs.CV","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"d6a6908d86b4b1796263d1320ce26b18cb22d5ae26d28e038735c7ec52e3c191","abstract_canon_sha256":"b0e533970d7367fd1c53befc51a67321ee546f1ad0244ae1d4ebec4c9cbf13ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:30.350278Z","signature_b64":"VINM7BiuUTv0qR60iDllmlhGTnddbbc6jN07ww4UsVW1oFFUElDksHPHgsjjOcuSemdS0F0hnKzODUHulfyKAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2842e9b1a3403312cd173fcf516a22732a5ac82c0e938fd6b6cbaa3574da17ff","last_reissued_at":"2026-07-05T06:11:30.349901Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:30.349901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QPGesture: Quantization-Based and Phase-Guided Motion Matching for Natural Speech-Driven Gesture Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.HC","authors_text":"Haolin Zhuang, Lei Hao, Minglei Li, Sicheng Yang, Weihong Bao, Zhensong Zhang, Zhiyong Wu","submitted_at":"2023-05-18T16:31:25Z","abstract_excerpt":"Speech-driven gesture generation is highly challenging due to the random jitters of human motion. In addition, there is an inherent asynchronous relationship between human speech and gestures. To tackle these challenges, we introduce a novel quantization-based and phase-guided motion-matching framework. Specifically, we first present a gesture VQ-VAE module to learn a codebook to summarize meaningful gesture units. With each code representing a unique gesture, random jittering problems are alleviated effectively. We then use Levenshtein distance to align diverse gestures with different speech."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11094","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/2305.11094/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":"2305.11094","created_at":"2026-07-05T06:11:30.349957+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.11094v1","created_at":"2026-07-05T06:11:30.349957+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11094","created_at":"2026-07-05T06:11:30.349957+00:00"},{"alias_kind":"pith_short_12","alias_value":"FBBOTMNDIAZR","created_at":"2026-07-05T06:11:30.349957+00:00"},{"alias_kind":"pith_short_16","alias_value":"FBBOTMNDIAZRFTIX","created_at":"2026-07-05T06:11:30.349957+00:00"},{"alias_kind":"pith_short_8","alias_value":"FBBOTMND","created_at":"2026-07-05T06:11:30.349957+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FBBOTMNDIAZRFTIXH7HVC2RCOM","json":"https://pith.science/pith/FBBOTMNDIAZRFTIXH7HVC2RCOM.json","graph_json":"https://pith.science/api/pith-number/FBBOTMNDIAZRFTIXH7HVC2RCOM/graph.json","events_json":"https://pith.science/api/pith-number/FBBOTMNDIAZRFTIXH7HVC2RCOM/events.json","paper":"https://pith.science/paper/FBBOTMND"},"agent_actions":{"view_html":"https://pith.science/pith/FBBOTMNDIAZRFTIXH7HVC2RCOM","download_json":"https://pith.science/pith/FBBOTMNDIAZRFTIXH7HVC2RCOM.json","view_paper":"https://pith.science/paper/FBBOTMND","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.11094&json=true","fetch_graph":"https://pith.science/api/pith-number/FBBOTMNDIAZRFTIXH7HVC2RCOM/graph.json","fetch_events":"https://pith.science/api/pith-number/FBBOTMNDIAZRFTIXH7HVC2RCOM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FBBOTMNDIAZRFTIXH7HVC2RCOM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FBBOTMNDIAZRFTIXH7HVC2RCOM/action/storage_attestation","attest_author":"https://pith.science/pith/FBBOTMNDIAZRFTIXH7HVC2RCOM/action/author_attestation","sign_citation":"https://pith.science/pith/FBBOTMNDIAZRFTIXH7HVC2RCOM/action/citation_signature","submit_replication":"https://pith.science/pith/FBBOTMNDIAZRFTIXH7HVC2RCOM/action/replication_record"}},"created_at":"2026-07-05T06:11:30.349957+00:00","updated_at":"2026-07-05T06:11:30.349957+00:00"}