{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:GABSVJAHBDCRQL7RBKZKXNNK6G","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":"5784a6f72404ec9a17348a64f16d28d93a0ab18a8501b771827c497dabc736cf","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-15T03:27:45Z","title_canon_sha256":"33db73c23540c640faecc75b95116d7271c4b033008a1113344595b8538dc8cb"},"schema_version":"1.0","source":{"id":"2110.07840","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.07840","created_at":"2026-07-05T03:22:50Z"},{"alias_kind":"arxiv_version","alias_value":"2110.07840v1","created_at":"2026-07-05T03:22:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.07840","created_at":"2026-07-05T03:22:50Z"},{"alias_kind":"pith_short_12","alias_value":"GABSVJAHBDCR","created_at":"2026-07-05T03:22:50Z"},{"alias_kind":"pith_short_16","alias_value":"GABSVJAHBDCRQL7R","created_at":"2026-07-05T03:22:50Z"},{"alias_kind":"pith_short_8","alias_value":"GABSVJAH","created_at":"2026-07-05T03:22:50Z"}],"graph_snapshots":[{"event_id":"sha256:4f7d349ae5d0784965483b2d2ca184a8b377811999a48a8dc5f0df43f7d27f1b","target":"graph","created_at":"2026-07-05T03:22:50Z","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/2110.07840/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper describes ESPnet2-TTS, an end-to-end text-to-speech (E2E-TTS) toolkit. ESPnet2-TTS extends our earlier version, ESPnet-TTS, by adding many new features, including: on-the-fly flexible pre-processing, joint training with neural vocoders, and state-of-the-art TTS models with extensions like full-band E2E text-to-waveform modeling, which simplify the training pipeline and further enhance TTS performance. The unified design of our recipes enables users to quickly reproduce state-of-the-art E2E-TTS results. We also provide many pre-trained models in a unified Python interface for inferen","authors_text":"Jiatong Shi, Peter Wu, Ryuichi Yamamoto, Shinji Watanabe, Shinnosuke Takamichi, Takaaki Saeki, Takenori Yoshimura, Tomoki Hayashi, Yooncheol Ju, Yusuke Yasuda","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-15T03:27:45Z","title":"ESPnet2-TTS: Extending the Edge of TTS Research"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.07840","kind":"arxiv","version":1},"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":"sha256:88a1e7925924c86e9d6362fc9f4d385cd66e18f4e9750147247667f2e9793c5a","target":"record","created_at":"2026-07-05T03:22:50Z","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":"5784a6f72404ec9a17348a64f16d28d93a0ab18a8501b771827c497dabc736cf","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-15T03:27:45Z","title_canon_sha256":"33db73c23540c640faecc75b95116d7271c4b033008a1113344595b8538dc8cb"},"schema_version":"1.0","source":{"id":"2110.07840","kind":"arxiv","version":1}},"canonical_sha256":"30032aa40708c5182ff10ab2abb5aaf1a02b71e66e0dbc37e5ce65cc5d7fd18b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30032aa40708c5182ff10ab2abb5aaf1a02b71e66e0dbc37e5ce65cc5d7fd18b","first_computed_at":"2026-07-05T03:22:50.554713Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:22:50.554713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sgA7kMQdTXrOMdcbJmowMp4eHxMCtYyMqycSb38qwELkI25foO1R/uPNa2h1EoCPif1mF7Irw5QjZJy9YDoTDw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:22:50.555172Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.07840","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:88a1e7925924c86e9d6362fc9f4d385cd66e18f4e9750147247667f2e9793c5a","sha256:4f7d349ae5d0784965483b2d2ca184a8b377811999a48a8dc5f0df43f7d27f1b"],"state_sha256":"e03428e396cd095533a8f6f14fbd34cf97e24382f575a17478050e61119c84e8"}