{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:X3JCSHWARKVLBFXFKD7TXNX3TF","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":"3478069c9cbca6872a32d6bebd30bf98868929880a585d6fe2e81c9757b8ac14","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-06-24T10:52:10Z","title_canon_sha256":"d01f5d350972228758a5e452500e81bac624dff88e9d459d319974d8a13ba060"},"schema_version":"1.0","source":{"id":"2106.12896","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.12896","created_at":"2026-07-05T02:52:28Z"},{"alias_kind":"arxiv_version","alias_value":"2106.12896v2","created_at":"2026-07-05T02:52:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.12896","created_at":"2026-07-05T02:52:28Z"},{"alias_kind":"pith_short_12","alias_value":"X3JCSHWARKVL","created_at":"2026-07-05T02:52:28Z"},{"alias_kind":"pith_short_16","alias_value":"X3JCSHWARKVLBFXF","created_at":"2026-07-05T02:52:28Z"},{"alias_kind":"pith_short_8","alias_value":"X3JCSHWA","created_at":"2026-07-05T02:52:28Z"}],"graph_snapshots":[{"event_id":"sha256:0b903917595fd7e7c75a3eb6a371e699e3893d5ceffa34f5978150f358670506","target":"graph","created_at":"2026-07-05T02:52:28Z","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/2106.12896/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Whilst recent neural text-to-speech (TTS) approaches produce high-quality speech, they typically require a large amount of recordings from the target speaker. In previous work, a 3-step method was proposed to generate high-quality TTS while greatly reducing the amount of data required for training. However, we have observed a ceiling effect in the level of naturalness achievable for highly expressive voices when using this approach. In this paper, we present a method for building highly expressive TTS voices with as little as 15 minutes of speech data from the target speaker. Compared to the c","authors_text":"Abdelhamid Ezzerg, Bartosz Putrycz, Daniel Korzekwa, Goeric Huybrechts, Kamil Pokora, Raahil Shah, Thomas Merritt, Viacheslav Klimkov","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-06-24T10:52:10Z","title":"Non-Autoregressive TTS with Explicit Duration Modelling for Low-Resource Highly Expressive Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.12896","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":"sha256:207130aff599011863201cfab547fb56c238e5719ac047c332da5cd2a3abcb8a","target":"record","created_at":"2026-07-05T02:52:28Z","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":"3478069c9cbca6872a32d6bebd30bf98868929880a585d6fe2e81c9757b8ac14","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-06-24T10:52:10Z","title_canon_sha256":"d01f5d350972228758a5e452500e81bac624dff88e9d459d319974d8a13ba060"},"schema_version":"1.0","source":{"id":"2106.12896","kind":"arxiv","version":2}},"canonical_sha256":"bed2291ec08aaab096e550ff3bb6fb9956eb12d53680791a253d3910b4ff1947","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bed2291ec08aaab096e550ff3bb6fb9956eb12d53680791a253d3910b4ff1947","first_computed_at":"2026-07-05T02:52:28.852408Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:52:28.852408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UR0CKO0l838bT0xiN6Zi0MBVMu8uvH9n751Ox/6AW5uVJQUCCMIwgbTG4gjC2hN4xqC8oYy6omjF7JdkudwDDg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:52:28.852847Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.12896","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:207130aff599011863201cfab547fb56c238e5719ac047c332da5cd2a3abcb8a","sha256:0b903917595fd7e7c75a3eb6a371e699e3893d5ceffa34f5978150f358670506"],"state_sha256":"f36c4a2f996704be03ca83d0f4368587494636b753d3df8af5a42c6a840c896d"}