{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GABSVJAHBDCRQL7RBKZKXNNK6G","short_pith_number":"pith:GABSVJAH","schema_version":"1.0","canonical_sha256":"30032aa40708c5182ff10ab2abb5aaf1a02b71e66e0dbc37e5ce65cc5d7fd18b","source":{"kind":"arxiv","id":"2110.07840","version":1},"attestation_state":"computed","paper":{"title":"ESPnet2-TTS: Extending the Edge of TTS Research","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jiatong Shi, Peter Wu, Ryuichi Yamamoto, Shinji Watanabe, Shinnosuke Takamichi, Takaaki Saeki, Takenori Yoshimura, Tomoki Hayashi, Yooncheol Ju, Yusuke Yasuda","submitted_at":"2021-10-15T03:27:45Z","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"},"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":"2110.07840","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-15T03:27:45Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"33db73c23540c640faecc75b95116d7271c4b033008a1113344595b8538dc8cb","abstract_canon_sha256":"5784a6f72404ec9a17348a64f16d28d93a0ab18a8501b771827c497dabc736cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:22:50.555172Z","signature_b64":"sgA7kMQdTXrOMdcbJmowMp4eHxMCtYyMqycSb38qwELkI25foO1R/uPNa2h1EoCPif1mF7Irw5QjZJy9YDoTDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30032aa40708c5182ff10ab2abb5aaf1a02b71e66e0dbc37e5ce65cc5d7fd18b","last_reissued_at":"2026-07-05T03:22:50.554713Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:22:50.554713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ESPnet2-TTS: Extending the Edge of TTS Research","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jiatong Shi, Peter Wu, Ryuichi Yamamoto, Shinji Watanabe, Shinnosuke Takamichi, Takaaki Saeki, Takenori Yoshimura, Tomoki Hayashi, Yooncheol Ju, Yusuke Yasuda","submitted_at":"2021-10-15T03:27:45Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.07840","kind":"arxiv","version":1},"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/2110.07840/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":"2110.07840","created_at":"2026-07-05T03:22:50.554771+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.07840v1","created_at":"2026-07-05T03:22:50.554771+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.07840","created_at":"2026-07-05T03:22:50.554771+00:00"},{"alias_kind":"pith_short_12","alias_value":"GABSVJAHBDCR","created_at":"2026-07-05T03:22:50.554771+00:00"},{"alias_kind":"pith_short_16","alias_value":"GABSVJAHBDCRQL7R","created_at":"2026-07-05T03:22:50.554771+00:00"},{"alias_kind":"pith_short_8","alias_value":"GABSVJAH","created_at":"2026-07-05T03:22:50.554771+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.00861","citing_title":"Voice Mapping of Text-to-Speech Systems: A Metric-Based Approach for Voice Quality Assessment","ref_index":58,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GABSVJAHBDCRQL7RBKZKXNNK6G","json":"https://pith.science/pith/GABSVJAHBDCRQL7RBKZKXNNK6G.json","graph_json":"https://pith.science/api/pith-number/GABSVJAHBDCRQL7RBKZKXNNK6G/graph.json","events_json":"https://pith.science/api/pith-number/GABSVJAHBDCRQL7RBKZKXNNK6G/events.json","paper":"https://pith.science/paper/GABSVJAH"},"agent_actions":{"view_html":"https://pith.science/pith/GABSVJAHBDCRQL7RBKZKXNNK6G","download_json":"https://pith.science/pith/GABSVJAHBDCRQL7RBKZKXNNK6G.json","view_paper":"https://pith.science/paper/GABSVJAH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.07840&json=true","fetch_graph":"https://pith.science/api/pith-number/GABSVJAHBDCRQL7RBKZKXNNK6G/graph.json","fetch_events":"https://pith.science/api/pith-number/GABSVJAHBDCRQL7RBKZKXNNK6G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GABSVJAHBDCRQL7RBKZKXNNK6G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GABSVJAHBDCRQL7RBKZKXNNK6G/action/storage_attestation","attest_author":"https://pith.science/pith/GABSVJAHBDCRQL7RBKZKXNNK6G/action/author_attestation","sign_citation":"https://pith.science/pith/GABSVJAHBDCRQL7RBKZKXNNK6G/action/citation_signature","submit_replication":"https://pith.science/pith/GABSVJAHBDCRQL7RBKZKXNNK6G/action/replication_record"}},"created_at":"2026-07-05T03:22:50.554771+00:00","updated_at":"2026-07-05T03:22:50.554771+00:00"}