{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:RXW4H4LT22QYPU2O726TS3RP5Q","short_pith_number":"pith:RXW4H4LT","canonical_record":{"source":{"id":"1808.10128","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-30T05:51:30Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"f1d6a4408faadafcab9174a2c3443d57ba3974b420afd5da4155d63a714588d5","abstract_canon_sha256":"b359785ca930cfcf8cdc0eeb33d55ba5adf2b216fe0593de7b5eda950064091f"},"schema_version":"1.0"},"canonical_sha256":"8dedc3f173d6a187d34efebd396e2fec361019ab37b873badfca8069b88241ac","source":{"kind":"arxiv","id":"1808.10128","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.10128","created_at":"2026-05-18T00:06:49Z"},{"alias_kind":"arxiv_version","alias_value":"1808.10128v1","created_at":"2026-05-18T00:06:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.10128","created_at":"2026-05-18T00:06:49Z"},{"alias_kind":"pith_short_12","alias_value":"RXW4H4LT22QY","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RXW4H4LT22QYPU2O","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RXW4H4LT","created_at":"2026-05-18T12:32:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:RXW4H4LT22QYPU2O726TS3RP5Q","target":"record","payload":{"canonical_record":{"source":{"id":"1808.10128","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-30T05:51:30Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"f1d6a4408faadafcab9174a2c3443d57ba3974b420afd5da4155d63a714588d5","abstract_canon_sha256":"b359785ca930cfcf8cdc0eeb33d55ba5adf2b216fe0593de7b5eda950064091f"},"schema_version":"1.0"},"canonical_sha256":"8dedc3f173d6a187d34efebd396e2fec361019ab37b873badfca8069b88241ac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:49.746623Z","signature_b64":"UkAW9CObMk4N6eia6RIzk2KZzqxADPlDDK3/5jB8R+e95TyUIQmNmYC6yVV7m4T+vngjOmcIdLnis722tb7iCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8dedc3f173d6a187d34efebd396e2fec361019ab37b873badfca8069b88241ac","last_reissued_at":"2026-05-18T00:06:49.745902Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:49.745902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.10128","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:06:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HpRuJn6H770Xne9GJ9CZ92gL9PeOnbMEAV4mhXhzLq+ZSB0XZSsbSHCZy2DfkS4PcSMuCfgeM7hgMtdLmjTaAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T22:58:26.446886Z"},"content_sha256":"a6340cd0a6f4e714678dff799b0b06cfeddad6d0cee1da733194e4a614e883c5","schema_version":"1.0","event_id":"sha256:a6340cd0a6f4e714678dff799b0b06cfeddad6d0cee1da733194e4a614e883c5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:RXW4H4LT22QYPU2O726TS3RP5Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semi-Supervised Training for Improving Data Efficiency in End-to-End Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"RJ Skerry-Ryan, Wei-Ning Hsu, Yu-An Chung, Yuxuan Wang, Yu Zhang","submitted_at":"2018-08-30T05:51:30Z","abstract_excerpt":"Although end-to-end text-to-speech (TTS) models such as Tacotron have shown excellent results, they typically require a sizable set of high-quality <text, audio> pairs for training, which are expensive to collect. In this paper, we propose a semi-supervised training framework to improve the data efficiency of Tacotron. The idea is to allow Tacotron to utilize textual and acoustic knowledge contained in large, publicly-available text and speech corpora. Importantly, these external data are unpaired and potentially noisy. Specifically, first we embed each word in the input text into word vectors"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.10128","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:06:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"357WihIh/hrjb131QQy8dFCMpm/nCGzqwVgHtelmkrJZDveqVCJFo3BCQgbnPs6xH+aUYuPsdJDdQ1i2DOfLDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T22:58:26.447573Z"},"content_sha256":"af29e53e4e42c20d28ba703804528114e8684b6aa224b199e84a01ef863974b4","schema_version":"1.0","event_id":"sha256:af29e53e4e42c20d28ba703804528114e8684b6aa224b199e84a01ef863974b4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RXW4H4LT22QYPU2O726TS3RP5Q/bundle.json","state_url":"https://pith.science/pith/RXW4H4LT22QYPU2O726TS3RP5Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RXW4H4LT22QYPU2O726TS3RP5Q/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-25T22:58:26Z","links":{"resolver":"https://pith.science/pith/RXW4H4LT22QYPU2O726TS3RP5Q","bundle":"https://pith.science/pith/RXW4H4LT22QYPU2O726TS3RP5Q/bundle.json","state":"https://pith.science/pith/RXW4H4LT22QYPU2O726TS3RP5Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RXW4H4LT22QYPU2O726TS3RP5Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:RXW4H4LT22QYPU2O726TS3RP5Q","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":"b359785ca930cfcf8cdc0eeb33d55ba5adf2b216fe0593de7b5eda950064091f","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-30T05:51:30Z","title_canon_sha256":"f1d6a4408faadafcab9174a2c3443d57ba3974b420afd5da4155d63a714588d5"},"schema_version":"1.0","source":{"id":"1808.10128","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.10128","created_at":"2026-05-18T00:06:49Z"},{"alias_kind":"arxiv_version","alias_value":"1808.10128v1","created_at":"2026-05-18T00:06:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.10128","created_at":"2026-05-18T00:06:49Z"},{"alias_kind":"pith_short_12","alias_value":"RXW4H4LT22QY","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RXW4H4LT22QYPU2O","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RXW4H4LT","created_at":"2026-05-18T12:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:af29e53e4e42c20d28ba703804528114e8684b6aa224b199e84a01ef863974b4","target":"graph","created_at":"2026-05-18T00:06:49Z","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"},"paper":{"abstract_excerpt":"Although end-to-end text-to-speech (TTS) models such as Tacotron have shown excellent results, they typically require a sizable set of high-quality <text, audio> pairs for training, which are expensive to collect. In this paper, we propose a semi-supervised training framework to improve the data efficiency of Tacotron. The idea is to allow Tacotron to utilize textual and acoustic knowledge contained in large, publicly-available text and speech corpora. Importantly, these external data are unpaired and potentially noisy. Specifically, first we embed each word in the input text into word vectors","authors_text":"RJ Skerry-Ryan, Wei-Ning Hsu, Yu-An Chung, Yuxuan Wang, Yu Zhang","cross_cats":["cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-30T05:51:30Z","title":"Semi-Supervised Training for Improving Data Efficiency in End-to-End Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.10128","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:a6340cd0a6f4e714678dff799b0b06cfeddad6d0cee1da733194e4a614e883c5","target":"record","created_at":"2026-05-18T00:06:49Z","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":"b359785ca930cfcf8cdc0eeb33d55ba5adf2b216fe0593de7b5eda950064091f","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-30T05:51:30Z","title_canon_sha256":"f1d6a4408faadafcab9174a2c3443d57ba3974b420afd5da4155d63a714588d5"},"schema_version":"1.0","source":{"id":"1808.10128","kind":"arxiv","version":1}},"canonical_sha256":"8dedc3f173d6a187d34efebd396e2fec361019ab37b873badfca8069b88241ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8dedc3f173d6a187d34efebd396e2fec361019ab37b873badfca8069b88241ac","first_computed_at":"2026-05-18T00:06:49.745902Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:06:49.745902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UkAW9CObMk4N6eia6RIzk2KZzqxADPlDDK3/5jB8R+e95TyUIQmNmYC6yVV7m4T+vngjOmcIdLnis722tb7iCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:06:49.746623Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.10128","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a6340cd0a6f4e714678dff799b0b06cfeddad6d0cee1da733194e4a614e883c5","sha256:af29e53e4e42c20d28ba703804528114e8684b6aa224b199e84a01ef863974b4"],"state_sha256":"3701f7a79ef5824f34f1d8dc8b756bf5c1e36f8f77d345e83f3ffb9c2446a876"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4nuGn/x86dtqf3rB506WZpWhnWaBEcUeNzg5OK0e84eNvUZaVBzbgC6tXw4ptMtDK5FbIwMZZoALaN4WLLv5CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T22:58:26.451187Z","bundle_sha256":"597fce1f1c4b21e5ade5df8b54c6321794e1233b04060ac5a2b6c94f330469f7"}}