{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VH5RUQQWXQBS4SS445G5DMDGYI","short_pith_number":"pith:VH5RUQQW","schema_version":"1.0","canonical_sha256":"a9fb1a4216bc032e4a5ce74dd1b066c224a55f1f48ac58fe9515dd5c149a389a","source":{"kind":"arxiv","id":"2508.16188","version":2},"attestation_state":"computed","paper":{"title":"Seeing is Believing: Emotion-Aware Audio-Visual Language Modeling for Expressive Speech Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Hirofumi Inaguma, Jiachen Lian, Paden Tomasello, Philipp Koehn, Weiting Tan, Xutai Ma","submitted_at":"2025-08-22T08:08:45Z","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"},"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":"2508.16188","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-22T08:08:45Z","cross_cats_sorted":["cs.CV","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"aba3c53e8d1ea23e675ffeb38d068305ac40f9e78aff3f6ce30412c39cc1ad94","abstract_canon_sha256":"f70ae6ca44efce5188e9943e240e16e798cb0509e93d931b53d728f1eaf1f0ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:29.023936Z","signature_b64":"3wGYaX7ZRnfjSGFeLcD8/xnCxP0hDQvwm69AbLrTYTq2UoEgMfs92Pc7ac20bmS39qW1SPv0FITubwMSrsnHDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9fb1a4216bc032e4a5ce74dd1b066c224a55f1f48ac58fe9515dd5c149a389a","last_reissued_at":"2026-07-05T12:00:29.023439Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:29.023439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Seeing is Believing: Emotion-Aware Audio-Visual Language Modeling for Expressive Speech Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Hirofumi Inaguma, Jiachen Lian, Paden Tomasello, Philipp Koehn, Weiting Tan, Xutai Ma","submitted_at":"2025-08-22T08:08:45Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.16188","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/2508.16188/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":"2508.16188","created_at":"2026-07-05T12:00:29.023506+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.16188v2","created_at":"2026-07-05T12:00:29.023506+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.16188","created_at":"2026-07-05T12:00:29.023506+00:00"},{"alias_kind":"pith_short_12","alias_value":"VH5RUQQWXQBS","created_at":"2026-07-05T12:00:29.023506+00:00"},{"alias_kind":"pith_short_16","alias_value":"VH5RUQQWXQBS4SS4","created_at":"2026-07-05T12:00:29.023506+00:00"},{"alias_kind":"pith_short_8","alias_value":"VH5RUQQW","created_at":"2026-07-05T12:00:29.023506+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/VH5RUQQWXQBS4SS445G5DMDGYI","json":"https://pith.science/pith/VH5RUQQWXQBS4SS445G5DMDGYI.json","graph_json":"https://pith.science/api/pith-number/VH5RUQQWXQBS4SS445G5DMDGYI/graph.json","events_json":"https://pith.science/api/pith-number/VH5RUQQWXQBS4SS445G5DMDGYI/events.json","paper":"https://pith.science/paper/VH5RUQQW"},"agent_actions":{"view_html":"https://pith.science/pith/VH5RUQQWXQBS4SS445G5DMDGYI","download_json":"https://pith.science/pith/VH5RUQQWXQBS4SS445G5DMDGYI.json","view_paper":"https://pith.science/paper/VH5RUQQW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.16188&json=true","fetch_graph":"https://pith.science/api/pith-number/VH5RUQQWXQBS4SS445G5DMDGYI/graph.json","fetch_events":"https://pith.science/api/pith-number/VH5RUQQWXQBS4SS445G5DMDGYI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VH5RUQQWXQBS4SS445G5DMDGYI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VH5RUQQWXQBS4SS445G5DMDGYI/action/storage_attestation","attest_author":"https://pith.science/pith/VH5RUQQWXQBS4SS445G5DMDGYI/action/author_attestation","sign_citation":"https://pith.science/pith/VH5RUQQWXQBS4SS445G5DMDGYI/action/citation_signature","submit_replication":"https://pith.science/pith/VH5RUQQWXQBS4SS445G5DMDGYI/action/replication_record"}},"created_at":"2026-07-05T12:00:29.023506+00:00","updated_at":"2026-07-05T12:00:29.023506+00:00"}