{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:LLA67MFAK5IAY2O6MW555ETISI","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":"83215df6b86cfe0672aff9b274f10982db92f0f7d83dce41ab09b461f9d3eebc","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-05-18T06:55:38Z","title_canon_sha256":"f1969b476bf43392e5e7e78c2658fbbcd3c81fba3ec7a8124dbb411b3c1314fb"},"schema_version":"1.0","source":{"id":"2005.08484","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.08484","created_at":"2026-07-05T01:26:41Z"},{"alias_kind":"arxiv_version","alias_value":"2005.08484v2","created_at":"2026-07-05T01:26:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.08484","created_at":"2026-07-05T01:26:41Z"},{"alias_kind":"pith_short_12","alias_value":"LLA67MFAK5IA","created_at":"2026-07-05T01:26:41Z"},{"alias_kind":"pith_short_16","alias_value":"LLA67MFAK5IAY2O6","created_at":"2026-07-05T01:26:41Z"},{"alias_kind":"pith_short_8","alias_value":"LLA67MFA","created_at":"2026-07-05T01:26:41Z"}],"graph_snapshots":[{"event_id":"sha256:2d07925ce05672f131dbdcd73c2a6b9336bd21b4371628edaa6da7c5b4a543cd","target":"graph","created_at":"2026-07-05T01:26:41Z","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/2005.08484/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On account of growing demands for personalization, the need for a so-called few-shot TTS system that clones speakers with only a few data is emerging. To address this issue, we propose Attentron, a few-shot TTS model that clones voices of speakers unseen during training. It introduces two special encoders, each serving different purposes. A fine-grained encoder extracts variable-length style information via an attention mechanism, and a coarse-grained encoder greatly stabilizes the speech synthesis, circumventing unintelligible gibberish even for synthesizing speech of unseen speakers. In addi","authors_text":"Dongyoung Kim, Seungju Han, Seungwoo Choi, Sungjoo Ha","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-05-18T06:55:38Z","title":"Attentron: Few-Shot Text-to-Speech Utilizing Attention-Based Variable-Length Embedding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.08484","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":"sha256:8363f8706f1fda3955b952f0b618c26d098cb30e2b99ca76c00811f708b402d3","target":"record","created_at":"2026-07-05T01:26:41Z","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":"83215df6b86cfe0672aff9b274f10982db92f0f7d83dce41ab09b461f9d3eebc","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-05-18T06:55:38Z","title_canon_sha256":"f1969b476bf43392e5e7e78c2658fbbcd3c81fba3ec7a8124dbb411b3c1314fb"},"schema_version":"1.0","source":{"id":"2005.08484","kind":"arxiv","version":2}},"canonical_sha256":"5ac1efb0a057500c69de65bbde9268923ffce74bd60bec1d52f6779b6b97420f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5ac1efb0a057500c69de65bbde9268923ffce74bd60bec1d52f6779b6b97420f","first_computed_at":"2026-07-05T01:26:41.439733Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:26:41.439733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RyYUCH0vtwNXNdciwoc3kVDGnIHLWl+5si4CHIwZNW7OSPXC0GkMwjSmkOZ7FhRXjPwad9tP12AsJe84FuTRCA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:26:41.440243Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.08484","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8363f8706f1fda3955b952f0b618c26d098cb30e2b99ca76c00811f708b402d3","sha256:2d07925ce05672f131dbdcd73c2a6b9336bd21b4371628edaa6da7c5b4a543cd"],"state_sha256":"4a8e95e74256ace915a041cb17fd088ae173275f2ed781a460f466f6b24dd8f3"}