{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LPOIODXA5ETH3MQTMQKNYRX2Q3","short_pith_number":"pith:LPOIODXA","schema_version":"1.0","canonical_sha256":"5bdc870ee0e9267db2136414dc46fa86d2a64d520cc88f85a73ef576a1a70cde","source":{"kind":"arxiv","id":"2509.15626","version":4},"attestation_state":"computed","paper":{"title":"LibriTTS-VI: A Public Corpus and Novel Methods for Efficient Voice Impression Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Emiru Tsunoo, Junki Ohmura, Toshiyuki Kumakura, Toshiyuki Sekiya, Yuki Ito","submitted_at":"2025-09-19T05:43:15Z","abstract_excerpt":"Numerical voice impression (VI) control (e.g., scaling brightness) enables fine-grained control in text-to-speech (TTS). However, it faces two challenges: no public corpus and impression leakage, where reference audio biases synthesized voice away from the target VI. To address the first challenge, we introduce LibriTTS-VI, the first public VI corpus built on LibriTTS-R. For the second, we hypothesize a single reference causes leakage by entangling speaker identity and VI. To mitigate this, we propose 1) disentangled training with two utterances from the same speaker for speaker and VI conditi"},"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":"2509.15626","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-09-19T05:43:15Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"a7bb8e3ad629e8a7d49f6760066cdad23fab5755b7bf1796f86b394939454508","abstract_canon_sha256":"9862e8472ebb91800c18abdff3ad47e114007fca5ce3a64a0caea7fba88a262d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:09:51.122184Z","signature_b64":"51H85uEO3ZCKnGv5kPpy85h9FnL0iyvwbE83UddvH7jfKF4s5yRICn4eC2qTXqMBSTd2a0UdUcwe7R7tgILiBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bdc870ee0e9267db2136414dc46fa86d2a64d520cc88f85a73ef576a1a70cde","last_reissued_at":"2026-06-19T16:09:51.121772Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:09:51.121772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LibriTTS-VI: A Public Corpus and Novel Methods for Efficient Voice Impression Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Emiru Tsunoo, Junki Ohmura, Toshiyuki Kumakura, Toshiyuki Sekiya, Yuki Ito","submitted_at":"2025-09-19T05:43:15Z","abstract_excerpt":"Numerical voice impression (VI) control (e.g., scaling brightness) enables fine-grained control in text-to-speech (TTS). However, it faces two challenges: no public corpus and impression leakage, where reference audio biases synthesized voice away from the target VI. To address the first challenge, we introduce LibriTTS-VI, the first public VI corpus built on LibriTTS-R. For the second, we hypothesize a single reference causes leakage by entangling speaker identity and VI. To mitigate this, we propose 1) disentangled training with two utterances from the same speaker for speaker and VI conditi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.15626","kind":"arxiv","version":4},"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/2509.15626/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":"2509.15626","created_at":"2026-06-19T16:09:51.121826+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.15626v4","created_at":"2026-06-19T16:09:51.121826+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.15626","created_at":"2026-06-19T16:09:51.121826+00:00"},{"alias_kind":"pith_short_12","alias_value":"LPOIODXA5ETH","created_at":"2026-06-19T16:09:51.121826+00:00"},{"alias_kind":"pith_short_16","alias_value":"LPOIODXA5ETH3MQT","created_at":"2026-06-19T16:09:51.121826+00:00"},{"alias_kind":"pith_short_8","alias_value":"LPOIODXA","created_at":"2026-06-19T16:09:51.121826+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/LPOIODXA5ETH3MQTMQKNYRX2Q3","json":"https://pith.science/pith/LPOIODXA5ETH3MQTMQKNYRX2Q3.json","graph_json":"https://pith.science/api/pith-number/LPOIODXA5ETH3MQTMQKNYRX2Q3/graph.json","events_json":"https://pith.science/api/pith-number/LPOIODXA5ETH3MQTMQKNYRX2Q3/events.json","paper":"https://pith.science/paper/LPOIODXA"},"agent_actions":{"view_html":"https://pith.science/pith/LPOIODXA5ETH3MQTMQKNYRX2Q3","download_json":"https://pith.science/pith/LPOIODXA5ETH3MQTMQKNYRX2Q3.json","view_paper":"https://pith.science/paper/LPOIODXA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.15626&json=true","fetch_graph":"https://pith.science/api/pith-number/LPOIODXA5ETH3MQTMQKNYRX2Q3/graph.json","fetch_events":"https://pith.science/api/pith-number/LPOIODXA5ETH3MQTMQKNYRX2Q3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LPOIODXA5ETH3MQTMQKNYRX2Q3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LPOIODXA5ETH3MQTMQKNYRX2Q3/action/storage_attestation","attest_author":"https://pith.science/pith/LPOIODXA5ETH3MQTMQKNYRX2Q3/action/author_attestation","sign_citation":"https://pith.science/pith/LPOIODXA5ETH3MQTMQKNYRX2Q3/action/citation_signature","submit_replication":"https://pith.science/pith/LPOIODXA5ETH3MQTMQKNYRX2Q3/action/replication_record"}},"created_at":"2026-06-19T16:09:51.121826+00:00","updated_at":"2026-06-19T16:09:51.121826+00:00"}