{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:LO64NP6N2N3IY3A4GTQU7IQAIV","short_pith_number":"pith:LO64NP6N","canonical_record":{"source":{"id":"1807.11470","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2018-07-30T17:59:28Z","cross_cats_sorted":["cs.LG","cs.SD","stat.ML"],"title_canon_sha256":"492817191146355e8f4554b25c2490905fc714bb77ec582be42eb932c4a77c19","abstract_canon_sha256":"ba718557f56be0a2deed3fab4dbe76a8a08b95d4f6d4ee3129fb0adf35f70b82"},"schema_version":"1.0"},"canonical_sha256":"5bbdc6bfcdd3768c6c1c34e14fa2004551f48b96ceb00b9ddb5e845724e2e3a2","source":{"kind":"arxiv","id":"1807.11470","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.11470","created_at":"2026-05-18T00:06:11Z"},{"alias_kind":"arxiv_version","alias_value":"1807.11470v3","created_at":"2026-05-18T00:06:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.11470","created_at":"2026-05-18T00:06:11Z"},{"alias_kind":"pith_short_12","alias_value":"LO64NP6N2N3I","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LO64NP6N2N3IY3A4","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LO64NP6N","created_at":"2026-05-18T12:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:LO64NP6N2N3IY3A4GTQU7IQAIV","target":"record","payload":{"canonical_record":{"source":{"id":"1807.11470","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2018-07-30T17:59:28Z","cross_cats_sorted":["cs.LG","cs.SD","stat.ML"],"title_canon_sha256":"492817191146355e8f4554b25c2490905fc714bb77ec582be42eb932c4a77c19","abstract_canon_sha256":"ba718557f56be0a2deed3fab4dbe76a8a08b95d4f6d4ee3129fb0adf35f70b82"},"schema_version":"1.0"},"canonical_sha256":"5bbdc6bfcdd3768c6c1c34e14fa2004551f48b96ceb00b9ddb5e845724e2e3a2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:11.201138Z","signature_b64":"354OycKUqoJruldswqEec4McEYtPeCvqlc7xlruI2bZ/SEgu7mc0b7R8L5A/zAYikf0ariGmk3sl2BqFXO88Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bbdc6bfcdd3768c6c1c34e14fa2004551f48b96ceb00b9ddb5e845724e2e3a2","last_reissued_at":"2026-05-18T00:06:11.200523Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:11.200523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.11470","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:06:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oxJOYNr2qXpt1JaM7ELCYvfI8tpsZr8IxUPJ89+iUtRRRennrYMx3aoy3ItNaYA9sc7v5e98GXQ3gXuYrM5BAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T18:57:47.925270Z"},"content_sha256":"cc3c14e75b275ebc25ebbb62d298d6d8ecbed224606f613d43b9780cd2060c2e","schema_version":"1.0","event_id":"sha256:cc3c14e75b275ebc25ebbb62d298d6d8ecbed224606f613d43b9780cd2060c2e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:LO64NP6N2N3IY3A4GTQU7IQAIV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Encoder-Decoder Models for Unsupervised Learning of Controllable Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Gustav Eje Henter, Jaime Lorenzo-Trueba, Junichi Yamagishi, Xin Wang","submitted_at":"2018-07-30T17:59:28Z","abstract_excerpt":"Generating versatile and appropriate synthetic speech requires control over the output expression separate from the spoken text. Important non-textual speech variation is seldom annotated, in which case output control must be learned in an unsupervised fashion. In this paper, we perform an in-depth study of methods for unsupervised learning of control in statistical speech synthesis. For example, we show that popular unsupervised training heuristics can be interpreted as variational inference in certain autoencoder models. We additionally connect these models to VQ-VAEs, another, recently-prop"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.11470","kind":"arxiv","version":3},"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":"2026-05-18T00:06:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2JNzmUvI5GBOjnBrR9KlFV+G5FeSkHaOSILctVOiXe+qGQjdyGaNWO7y/vbJmbZUEaZ50EesNunOL1wkAJ5dBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T18:57:47.925651Z"},"content_sha256":"8245c597c7c9ed87df72eb4de8a2c3dc127cc7cf58365105e6f88c94bbd6127c","schema_version":"1.0","event_id":"sha256:8245c597c7c9ed87df72eb4de8a2c3dc127cc7cf58365105e6f88c94bbd6127c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LO64NP6N2N3IY3A4GTQU7IQAIV/bundle.json","state_url":"https://pith.science/pith/LO64NP6N2N3IY3A4GTQU7IQAIV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LO64NP6N2N3IY3A4GTQU7IQAIV/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":"2026-05-30T18:57:47Z","links":{"resolver":"https://pith.science/pith/LO64NP6N2N3IY3A4GTQU7IQAIV","bundle":"https://pith.science/pith/LO64NP6N2N3IY3A4GTQU7IQAIV/bundle.json","state":"https://pith.science/pith/LO64NP6N2N3IY3A4GTQU7IQAIV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LO64NP6N2N3IY3A4GTQU7IQAIV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:LO64NP6N2N3IY3A4GTQU7IQAIV","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":"ba718557f56be0a2deed3fab4dbe76a8a08b95d4f6d4ee3129fb0adf35f70b82","cross_cats_sorted":["cs.LG","cs.SD","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2018-07-30T17:59:28Z","title_canon_sha256":"492817191146355e8f4554b25c2490905fc714bb77ec582be42eb932c4a77c19"},"schema_version":"1.0","source":{"id":"1807.11470","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.11470","created_at":"2026-05-18T00:06:11Z"},{"alias_kind":"arxiv_version","alias_value":"1807.11470v3","created_at":"2026-05-18T00:06:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.11470","created_at":"2026-05-18T00:06:11Z"},{"alias_kind":"pith_short_12","alias_value":"LO64NP6N2N3I","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LO64NP6N2N3IY3A4","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LO64NP6N","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:8245c597c7c9ed87df72eb4de8a2c3dc127cc7cf58365105e6f88c94bbd6127c","target":"graph","created_at":"2026-05-18T00:06:11Z","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":"Generating versatile and appropriate synthetic speech requires control over the output expression separate from the spoken text. Important non-textual speech variation is seldom annotated, in which case output control must be learned in an unsupervised fashion. In this paper, we perform an in-depth study of methods for unsupervised learning of control in statistical speech synthesis. For example, we show that popular unsupervised training heuristics can be interpreted as variational inference in certain autoencoder models. We additionally connect these models to VQ-VAEs, another, recently-prop","authors_text":"Gustav Eje Henter, Jaime Lorenzo-Trueba, Junichi Yamagishi, Xin Wang","cross_cats":["cs.LG","cs.SD","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2018-07-30T17:59:28Z","title":"Deep Encoder-Decoder Models for Unsupervised Learning of Controllable Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.11470","kind":"arxiv","version":3},"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:cc3c14e75b275ebc25ebbb62d298d6d8ecbed224606f613d43b9780cd2060c2e","target":"record","created_at":"2026-05-18T00:06:11Z","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":"ba718557f56be0a2deed3fab4dbe76a8a08b95d4f6d4ee3129fb0adf35f70b82","cross_cats_sorted":["cs.LG","cs.SD","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2018-07-30T17:59:28Z","title_canon_sha256":"492817191146355e8f4554b25c2490905fc714bb77ec582be42eb932c4a77c19"},"schema_version":"1.0","source":{"id":"1807.11470","kind":"arxiv","version":3}},"canonical_sha256":"5bbdc6bfcdd3768c6c1c34e14fa2004551f48b96ceb00b9ddb5e845724e2e3a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5bbdc6bfcdd3768c6c1c34e14fa2004551f48b96ceb00b9ddb5e845724e2e3a2","first_computed_at":"2026-05-18T00:06:11.200523Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:06:11.200523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"354OycKUqoJruldswqEec4McEYtPeCvqlc7xlruI2bZ/SEgu7mc0b7R8L5A/zAYikf0ariGmk3sl2BqFXO88Bg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:06:11.201138Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.11470","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc3c14e75b275ebc25ebbb62d298d6d8ecbed224606f613d43b9780cd2060c2e","sha256:8245c597c7c9ed87df72eb4de8a2c3dc127cc7cf58365105e6f88c94bbd6127c"],"state_sha256":"5af10e1b25bdd69afe8945ccb09bdec0aaab59ed8897c9d44f916e1a90ddaa63"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NLHQmWQHz7pYpQ4cW69W57LtLFEIfh7tiGmg/etSGNWtroFfKpyAu6QFm/7uRH9MXaCouGUG6MQTvA7KaVg6AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T18:57:47.928154Z","bundle_sha256":"fa73fb60831781033220cd8c5eaaefe17dc27d1e78d215e88ae4e7875e46810c"}}