{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KAAEWOSPJJA5SORVWGBSQDMTBE","short_pith_number":"pith:KAAEWOSP","schema_version":"1.0","canonical_sha256":"50004b3a4f4a41d93a35b183280d93090b248603d01157a51d9d511ec55fac8f","source":{"kind":"arxiv","id":"2506.15085","version":2},"attestation_state":"computed","paper":{"title":"EmojiVoice: Towards long-term controllable expressivity in robot speech","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.RO","authors_text":"Angelica Lim, Bermet Burkanova, Gustav Eje Henter, Paige Tutt\\\"os\\'i, Shivam Mehta, Zachary Syvenky","submitted_at":"2025-06-18T02:49:50Z","abstract_excerpt":"Humans vary their expressivity when speaking for extended periods to maintain engagement with their listener. Although social robots tend to be deployed with ``expressive'' joyful voices, they lack this long-term variation found in human speech. Foundation model text-to-speech systems are beginning to mimic the expressivity in human speech, but they are difficult to deploy offline on robots. We present EmojiVoice, a free, customizable text-to-speech (TTS) toolkit that allows social roboticists to build temporally variable, expressive speech on social robots. We introduce emoji-prompting to all"},"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":"2506.15085","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-06-18T02:49:50Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"0d4b2e5996e34d1093d20e9e0c91d480b87c124146fc30f32f4c6b4113450a4d","abstract_canon_sha256":"954ae251396645bda041137915ea5fabc274029a8b46c1adebdb519ea42b87c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:36.461887Z","signature_b64":"saMHLrE3Fvqc7fjjauRzcSg6WMEN9gc3mepjYVwVcMShTLLd5Sky+siSA0KOylhN/zPF//2q7RgtYfmVttf9AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50004b3a4f4a41d93a35b183280d93090b248603d01157a51d9d511ec55fac8f","last_reissued_at":"2026-07-05T11:45:36.461375Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:36.461375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EmojiVoice: Towards long-term controllable expressivity in robot speech","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.RO","authors_text":"Angelica Lim, Bermet Burkanova, Gustav Eje Henter, Paige Tutt\\\"os\\'i, Shivam Mehta, Zachary Syvenky","submitted_at":"2025-06-18T02:49:50Z","abstract_excerpt":"Humans vary their expressivity when speaking for extended periods to maintain engagement with their listener. Although social robots tend to be deployed with ``expressive'' joyful voices, they lack this long-term variation found in human speech. Foundation model text-to-speech systems are beginning to mimic the expressivity in human speech, but they are difficult to deploy offline on robots. We present EmojiVoice, a free, customizable text-to-speech (TTS) toolkit that allows social roboticists to build temporally variable, expressive speech on social robots. We introduce emoji-prompting to all"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.15085","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/2506.15085/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":"2506.15085","created_at":"2026-07-05T11:45:36.461434+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.15085v2","created_at":"2026-07-05T11:45:36.461434+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.15085","created_at":"2026-07-05T11:45:36.461434+00:00"},{"alias_kind":"pith_short_12","alias_value":"KAAEWOSPJJA5","created_at":"2026-07-05T11:45:36.461434+00:00"},{"alias_kind":"pith_short_16","alias_value":"KAAEWOSPJJA5SORV","created_at":"2026-07-05T11:45:36.461434+00:00"},{"alias_kind":"pith_short_8","alias_value":"KAAEWOSP","created_at":"2026-07-05T11:45:36.461434+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.00537","citing_title":"The Prosody of Emojis","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KAAEWOSPJJA5SORVWGBSQDMTBE","json":"https://pith.science/pith/KAAEWOSPJJA5SORVWGBSQDMTBE.json","graph_json":"https://pith.science/api/pith-number/KAAEWOSPJJA5SORVWGBSQDMTBE/graph.json","events_json":"https://pith.science/api/pith-number/KAAEWOSPJJA5SORVWGBSQDMTBE/events.json","paper":"https://pith.science/paper/KAAEWOSP"},"agent_actions":{"view_html":"https://pith.science/pith/KAAEWOSPJJA5SORVWGBSQDMTBE","download_json":"https://pith.science/pith/KAAEWOSPJJA5SORVWGBSQDMTBE.json","view_paper":"https://pith.science/paper/KAAEWOSP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.15085&json=true","fetch_graph":"https://pith.science/api/pith-number/KAAEWOSPJJA5SORVWGBSQDMTBE/graph.json","fetch_events":"https://pith.science/api/pith-number/KAAEWOSPJJA5SORVWGBSQDMTBE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KAAEWOSPJJA5SORVWGBSQDMTBE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KAAEWOSPJJA5SORVWGBSQDMTBE/action/storage_attestation","attest_author":"https://pith.science/pith/KAAEWOSPJJA5SORVWGBSQDMTBE/action/author_attestation","sign_citation":"https://pith.science/pith/KAAEWOSPJJA5SORVWGBSQDMTBE/action/citation_signature","submit_replication":"https://pith.science/pith/KAAEWOSPJJA5SORVWGBSQDMTBE/action/replication_record"}},"created_at":"2026-07-05T11:45:36.461434+00:00","updated_at":"2026-07-05T11:45:36.461434+00:00"}