{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:4W2B5NAV5FBFWCWCC2R5OG3RP4","short_pith_number":"pith:4W2B5NAV","canonical_record":{"source":{"id":"2306.12020","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-21T05:11:39Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"a8a9178efbbcbd08f8c6cdeb3ea5c8b22ca808631ee569fee60c27ba4a425b5b","abstract_canon_sha256":"045004f4f96d3a1ecad763d061b357c05d43fb289f15187794882a4852418eef"},"schema_version":"1.0"},"canonical_sha256":"e5b41eb415e9425b0ac216a3d71b717f1cdad557d1adfcf5eb94df583a34f52e","source":{"kind":"arxiv","id":"2306.12020","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.12020","created_at":"2026-07-05T06:23:09Z"},{"alias_kind":"arxiv_version","alias_value":"2306.12020v1","created_at":"2026-07-05T06:23:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.12020","created_at":"2026-07-05T06:23:09Z"},{"alias_kind":"pith_short_12","alias_value":"4W2B5NAV5FBF","created_at":"2026-07-05T06:23:09Z"},{"alias_kind":"pith_short_16","alias_value":"4W2B5NAV5FBFWCWC","created_at":"2026-07-05T06:23:09Z"},{"alias_kind":"pith_short_8","alias_value":"4W2B5NAV","created_at":"2026-07-05T06:23:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:4W2B5NAV5FBFWCWCC2R5OG3RP4","target":"record","payload":{"canonical_record":{"source":{"id":"2306.12020","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-21T05:11:39Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"a8a9178efbbcbd08f8c6cdeb3ea5c8b22ca808631ee569fee60c27ba4a425b5b","abstract_canon_sha256":"045004f4f96d3a1ecad763d061b357c05d43fb289f15187794882a4852418eef"},"schema_version":"1.0"},"canonical_sha256":"e5b41eb415e9425b0ac216a3d71b717f1cdad557d1adfcf5eb94df583a34f52e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:23:09.563537Z","signature_b64":"ZmLPubpvrtozSe+SJBA61l7SAlYB1MO8XOUMvno9MynLTRM2Ff0X5BeQOpeYD44jATsgRxA4JFbKz2LI5AmvDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5b41eb415e9425b0ac216a3d71b717f1cdad557d1adfcf5eb94df583a34f52e","last_reissued_at":"2026-07-05T06:23:09.563209Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:23:09.563209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.12020","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:23:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z0yd4FbU7CdVLLUORRxkYoBWkdUbk8b24AxeIVgR7ulnYaXtF404r8YieI38vUu5pqZonRPBRpfr8KT5enSQBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:04:46.256508Z"},"content_sha256":"8cd79c72640e6d5949f00235b27de0e2892c3eddc355f4265fb80d87ec2879e7","schema_version":"1.0","event_id":"sha256:8cd79c72640e6d5949f00235b27de0e2892c3eddc355f4265fb80d87ec2879e7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:4W2B5NAV5FBFWCWCC2R5OG3RP4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Visual-Aware Text-to-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Mohan Zhou, Tao Mei, Tiejun Zhao, Ting Yao, Wei Zhang, Yalong Bai","submitted_at":"2023-06-21T05:11:39Z","abstract_excerpt":"Dynamically synthesizing talking speech that actively responds to a listening head is critical during the face-to-face interaction. For example, the speaker could take advantage of the listener's facial expression to adjust the tones, stressed syllables, or pauses. In this work, we present a new visual-aware text-to-speech (VA-TTS) task to synthesize speech conditioned on both textual inputs and sequential visual feedback (e.g., nod, smile) of the listener in face-to-face communication. Different from traditional text-to-speech, VA-TTS highlights the impact of visual modality. On this newly-mi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.12020","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/2306.12020/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:23:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hUIiw5c+24Wnf3aYzGYkwaYLuRu7JpaJ1be+X09GjOU/F92lvt6TQkzna57icFcG1CeGa//oOF4i5OPxguYuCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:04:46.257032Z"},"content_sha256":"2ca9c659e57c1c70fc2263bc6c6c616373b7472a633ee74e9596b3661774340e","schema_version":"1.0","event_id":"sha256:2ca9c659e57c1c70fc2263bc6c6c616373b7472a633ee74e9596b3661774340e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4W2B5NAV5FBFWCWCC2R5OG3RP4/bundle.json","state_url":"https://pith.science/pith/4W2B5NAV5FBFWCWCC2R5OG3RP4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4W2B5NAV5FBFWCWCC2R5OG3RP4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T06:04:46Z","links":{"resolver":"https://pith.science/pith/4W2B5NAV5FBFWCWCC2R5OG3RP4","bundle":"https://pith.science/pith/4W2B5NAV5FBFWCWCC2R5OG3RP4/bundle.json","state":"https://pith.science/pith/4W2B5NAV5FBFWCWCC2R5OG3RP4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4W2B5NAV5FBFWCWCC2R5OG3RP4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4W2B5NAV5FBFWCWCC2R5OG3RP4","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":"045004f4f96d3a1ecad763d061b357c05d43fb289f15187794882a4852418eef","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-21T05:11:39Z","title_canon_sha256":"a8a9178efbbcbd08f8c6cdeb3ea5c8b22ca808631ee569fee60c27ba4a425b5b"},"schema_version":"1.0","source":{"id":"2306.12020","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.12020","created_at":"2026-07-05T06:23:09Z"},{"alias_kind":"arxiv_version","alias_value":"2306.12020v1","created_at":"2026-07-05T06:23:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.12020","created_at":"2026-07-05T06:23:09Z"},{"alias_kind":"pith_short_12","alias_value":"4W2B5NAV5FBF","created_at":"2026-07-05T06:23:09Z"},{"alias_kind":"pith_short_16","alias_value":"4W2B5NAV5FBFWCWC","created_at":"2026-07-05T06:23:09Z"},{"alias_kind":"pith_short_8","alias_value":"4W2B5NAV","created_at":"2026-07-05T06:23:09Z"}],"graph_snapshots":[{"event_id":"sha256:2ca9c659e57c1c70fc2263bc6c6c616373b7472a633ee74e9596b3661774340e","target":"graph","created_at":"2026-07-05T06:23:09Z","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/2306.12020/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dynamically synthesizing talking speech that actively responds to a listening head is critical during the face-to-face interaction. For example, the speaker could take advantage of the listener's facial expression to adjust the tones, stressed syllables, or pauses. In this work, we present a new visual-aware text-to-speech (VA-TTS) task to synthesize speech conditioned on both textual inputs and sequential visual feedback (e.g., nod, smile) of the listener in face-to-face communication. Different from traditional text-to-speech, VA-TTS highlights the impact of visual modality. On this newly-mi","authors_text":"Mohan Zhou, Tao Mei, Tiejun Zhao, Ting Yao, Wei Zhang, Yalong Bai","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-21T05:11:39Z","title":"Visual-Aware Text-to-Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.12020","kind":"arxiv","version":1},"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":"sha256:8cd79c72640e6d5949f00235b27de0e2892c3eddc355f4265fb80d87ec2879e7","target":"record","created_at":"2026-07-05T06:23:09Z","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":"045004f4f96d3a1ecad763d061b357c05d43fb289f15187794882a4852418eef","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-21T05:11:39Z","title_canon_sha256":"a8a9178efbbcbd08f8c6cdeb3ea5c8b22ca808631ee569fee60c27ba4a425b5b"},"schema_version":"1.0","source":{"id":"2306.12020","kind":"arxiv","version":1}},"canonical_sha256":"e5b41eb415e9425b0ac216a3d71b717f1cdad557d1adfcf5eb94df583a34f52e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e5b41eb415e9425b0ac216a3d71b717f1cdad557d1adfcf5eb94df583a34f52e","first_computed_at":"2026-07-05T06:23:09.563209Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:23:09.563209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZmLPubpvrtozSe+SJBA61l7SAlYB1MO8XOUMvno9MynLTRM2Ff0X5BeQOpeYD44jATsgRxA4JFbKz2LI5AmvDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:23:09.563537Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.12020","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8cd79c72640e6d5949f00235b27de0e2892c3eddc355f4265fb80d87ec2879e7","sha256:2ca9c659e57c1c70fc2263bc6c6c616373b7472a633ee74e9596b3661774340e"],"state_sha256":"d69db0fcb3ac087fd0cad9f7305d5cda9e28c58654d1abf154c1b81dfc880434"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/2TFOHYH5ygUnw9XVpjo0yOgfWwoZ4h9kl5y/OeD0W89rlszMuwVaOZgcVPoz+veNFm42wL1fx3IuXgxF57bAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T06:04:46.263079Z","bundle_sha256":"3f66374ac2edaa0bcd2da9b998ff16429aae50cd34bbebf437975a6e58969422"}}