{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:7XLM6WJXBZMF2E2E6PDPPFVQYE","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":"c478ad37332e6b91f17b935057bfaf8fe9aa3026920538d9b29eb2441f8b6562","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-10-12T07:51:25Z","title_canon_sha256":"8f2ebe6fa3aa03f631045b3564829026722a2281375b1de1c9eee2ab7dbb8222"},"schema_version":"1.0","source":{"id":"2110.05798","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.05798","created_at":"2026-07-05T04:12:02Z"},{"alias_kind":"arxiv_version","alias_value":"2110.05798v2","created_at":"2026-07-05T04:12:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.05798","created_at":"2026-07-05T04:12:02Z"},{"alias_kind":"pith_short_12","alias_value":"7XLM6WJXBZMF","created_at":"2026-07-05T04:12:02Z"},{"alias_kind":"pith_short_16","alias_value":"7XLM6WJXBZMF2E2E","created_at":"2026-07-05T04:12:02Z"},{"alias_kind":"pith_short_8","alias_value":"7XLM6WJX","created_at":"2026-07-05T04:12:02Z"}],"graph_snapshots":[{"event_id":"sha256:3c1e3f2d1d5140d807e1dca29c4f6ce78623f42a988950e969823b416b4d6932","target":"graph","created_at":"2026-07-05T04:12:02Z","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/2110.05798/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training neural text-to-speech (TTS) models for a new speaker typically requires several hours of high quality speech data. Prior works on voice cloning attempt to address this challenge by adapting pre-trained multi-speaker TTS models for a new voice, using a few minutes of speech data of the new speaker. However, publicly available large multi-speaker datasets are often noisy, thereby resulting in TTS models that are not suitable for use in products. We address this challenge by proposing transfer-learning guidelines for adapting high quality single-speaker TTS models for a new speaker, usin","authors_text":"Boris Ginsburg, Jason Li, Paarth Neekhara","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-10-12T07:51:25Z","title":"Adapting TTS models For New Speakers using Transfer Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.05798","kind":"arxiv","version":2},"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":"sha256:6e609fb679223f85c4abdb90712e19e9570f3ae002189851635c6cb8e20e2d08","target":"record","created_at":"2026-07-05T04:12:02Z","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":"c478ad37332e6b91f17b935057bfaf8fe9aa3026920538d9b29eb2441f8b6562","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-10-12T07:51:25Z","title_canon_sha256":"8f2ebe6fa3aa03f631045b3564829026722a2281375b1de1c9eee2ab7dbb8222"},"schema_version":"1.0","source":{"id":"2110.05798","kind":"arxiv","version":2}},"canonical_sha256":"fdd6cf59370e585d1344f3c6f796b0c129bcd2d69189cdc5776cd2455f421581","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fdd6cf59370e585d1344f3c6f796b0c129bcd2d69189cdc5776cd2455f421581","first_computed_at":"2026-07-05T04:12:02.835762Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:12:02.835762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1UoPC6AxnMon1LU9LRjBVw8gylV9+svdChhlC6wGjHRqwsBQy9jrFkGuVyeKqQVE7Pse948ysCwY6lGyUKwlCg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:12:02.836336Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.05798","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e609fb679223f85c4abdb90712e19e9570f3ae002189851635c6cb8e20e2d08","sha256:3c1e3f2d1d5140d807e1dca29c4f6ce78623f42a988950e969823b416b4d6932"],"state_sha256":"2ace75e8ddcdd060d9a58707d0af573dcf64321201d04bcc6ad456e97594d8ed"}