{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4W2B5NAV5FBFWCWCC2R5OG3RP4","short_pith_number":"pith:4W2B5NAV","schema_version":"1.0","canonical_sha256":"e5b41eb415e9425b0ac216a3d71b717f1cdad557d1adfcf5eb94df583a34f52e","source":{"kind":"arxiv","id":"2306.12020","version":1},"attestation_state":"computed","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"},"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":"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2306.12020","created_at":"2026-07-05T06:23:09.563259+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.12020v1","created_at":"2026-07-05T06:23:09.563259+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.12020","created_at":"2026-07-05T06:23:09.563259+00:00"},{"alias_kind":"pith_short_12","alias_value":"4W2B5NAV5FBF","created_at":"2026-07-05T06:23:09.563259+00:00"},{"alias_kind":"pith_short_16","alias_value":"4W2B5NAV5FBFWCWC","created_at":"2026-07-05T06:23:09.563259+00:00"},{"alias_kind":"pith_short_8","alias_value":"4W2B5NAV","created_at":"2026-07-05T06:23:09.563259+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/4W2B5NAV5FBFWCWCC2R5OG3RP4","json":"https://pith.science/pith/4W2B5NAV5FBFWCWCC2R5OG3RP4.json","graph_json":"https://pith.science/api/pith-number/4W2B5NAV5FBFWCWCC2R5OG3RP4/graph.json","events_json":"https://pith.science/api/pith-number/4W2B5NAV5FBFWCWCC2R5OG3RP4/events.json","paper":"https://pith.science/paper/4W2B5NAV"},"agent_actions":{"view_html":"https://pith.science/pith/4W2B5NAV5FBFWCWCC2R5OG3RP4","download_json":"https://pith.science/pith/4W2B5NAV5FBFWCWCC2R5OG3RP4.json","view_paper":"https://pith.science/paper/4W2B5NAV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.12020&json=true","fetch_graph":"https://pith.science/api/pith-number/4W2B5NAV5FBFWCWCC2R5OG3RP4/graph.json","fetch_events":"https://pith.science/api/pith-number/4W2B5NAV5FBFWCWCC2R5OG3RP4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4W2B5NAV5FBFWCWCC2R5OG3RP4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4W2B5NAV5FBFWCWCC2R5OG3RP4/action/storage_attestation","attest_author":"https://pith.science/pith/4W2B5NAV5FBFWCWCC2R5OG3RP4/action/author_attestation","sign_citation":"https://pith.science/pith/4W2B5NAV5FBFWCWCC2R5OG3RP4/action/citation_signature","submit_replication":"https://pith.science/pith/4W2B5NAV5FBFWCWCC2R5OG3RP4/action/replication_record"}},"created_at":"2026-07-05T06:23:09.563259+00:00","updated_at":"2026-07-05T06:23:09.563259+00:00"}