{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VH5RUQQWXQBS4SS445G5DMDGYI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f70ae6ca44efce5188e9943e240e16e798cb0509e93d931b53d728f1eaf1f0ad","cross_cats_sorted":["cs.CV","cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-22T08:08:45Z","title_canon_sha256":"aba3c53e8d1ea23e675ffeb38d068305ac40f9e78aff3f6ce30412c39cc1ad94"},"schema_version":"1.0","source":{"id":"2508.16188","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.16188","created_at":"2026-07-05T12:00:29Z"},{"alias_kind":"arxiv_version","alias_value":"2508.16188v2","created_at":"2026-07-05T12:00:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.16188","created_at":"2026-07-05T12:00:29Z"},{"alias_kind":"pith_short_12","alias_value":"VH5RUQQWXQBS","created_at":"2026-07-05T12:00:29Z"},{"alias_kind":"pith_short_16","alias_value":"VH5RUQQWXQBS4SS4","created_at":"2026-07-05T12:00:29Z"},{"alias_kind":"pith_short_8","alias_value":"VH5RUQQW","created_at":"2026-07-05T12:00:29Z"}],"graph_snapshots":[{"event_id":"sha256:67b7810c3f897506d1ecff16e09b16671b2008940a9b8bf8365ada474f5ab744","target":"graph","created_at":"2026-07-05T12:00:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2508.16188/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present an Audio-Visual Language Model (AVLM) for expressive speech generation by integrating full-face visual cues into a pre-trained expressive speech model. We explore multiple visual encoders and multimodal fusion strategies during pre-training to identify the most effective integration approach. Subsequent fine-tuning on emotion recognition and expressive dialogue tasks yields substantial gains over speech-only baselines (e.g., +5 F1 in emotion recognition). AVLM highlights the value of expressive visual information in guiding speech generation and offers a foundation for end-to-end mu","authors_text":"Hirofumi Inaguma, Jiachen Lian, Paden Tomasello, Philipp Koehn, Weiting Tan, Xutai Ma","cross_cats":["cs.CV","cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-22T08:08:45Z","title":"Seeing is Believing: Emotion-Aware Audio-Visual Language Modeling for Expressive Speech Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.16188","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7ec1bc192f61b8f72cc9d19681f3e6f2a145ba5a726842e93bd23f4ec0d34683","target":"record","created_at":"2026-07-05T12:00:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f70ae6ca44efce5188e9943e240e16e798cb0509e93d931b53d728f1eaf1f0ad","cross_cats_sorted":["cs.CV","cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-22T08:08:45Z","title_canon_sha256":"aba3c53e8d1ea23e675ffeb38d068305ac40f9e78aff3f6ce30412c39cc1ad94"},"schema_version":"1.0","source":{"id":"2508.16188","kind":"arxiv","version":2}},"canonical_sha256":"a9fb1a4216bc032e4a5ce74dd1b066c224a55f1f48ac58fe9515dd5c149a389a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9fb1a4216bc032e4a5ce74dd1b066c224a55f1f48ac58fe9515dd5c149a389a","first_computed_at":"2026-07-05T12:00:29.023439Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:00:29.023439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3wGYaX7ZRnfjSGFeLcD8/xnCxP0hDQvwm69AbLrTYTq2UoEgMfs92Pc7ac20bmS39qW1SPv0FITubwMSrsnHDg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:00:29.023936Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.16188","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ec1bc192f61b8f72cc9d19681f3e6f2a145ba5a726842e93bd23f4ec0d34683","sha256:67b7810c3f897506d1ecff16e09b16671b2008940a9b8bf8365ada474f5ab744"],"state_sha256":"a8f3eb9bdf34fe57ec4c0c7dca7b2aa466f48ebfafd84df63987f0e224cd6f3e"}