{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:DQBJTBIVOS7Q6W3JFBF3KVHPI2","short_pith_number":"pith:DQBJTBIV","canonical_record":{"source":{"id":"2110.03012","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-10-06T18:45:39Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"80e49dbdcc993b2f5692f141079c51177fac6ed4d039bde51b3ea33304606983","abstract_canon_sha256":"9fd08b7c149f7050583c1a6649c2ef692f68f14e95291681609442578d9b0067"},"schema_version":"1.0"},"canonical_sha256":"1c0299851574bf0f5b69284bb554ef46b11dc73e9148e4bc75fdda4d2655bfda","source":{"kind":"arxiv","id":"2110.03012","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.03012","created_at":"2026-07-05T04:09:15Z"},{"alias_kind":"arxiv_version","alias_value":"2110.03012v2","created_at":"2026-07-05T04:09:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03012","created_at":"2026-07-05T04:09:15Z"},{"alias_kind":"pith_short_12","alias_value":"DQBJTBIVOS7Q","created_at":"2026-07-05T04:09:15Z"},{"alias_kind":"pith_short_16","alias_value":"DQBJTBIVOS7Q6W3J","created_at":"2026-07-05T04:09:15Z"},{"alias_kind":"pith_short_8","alias_value":"DQBJTBIV","created_at":"2026-07-05T04:09:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:DQBJTBIVOS7Q6W3JFBF3KVHPI2","target":"record","payload":{"canonical_record":{"source":{"id":"2110.03012","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-10-06T18:45:39Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"80e49dbdcc993b2f5692f141079c51177fac6ed4d039bde51b3ea33304606983","abstract_canon_sha256":"9fd08b7c149f7050583c1a6649c2ef692f68f14e95291681609442578d9b0067"},"schema_version":"1.0"},"canonical_sha256":"1c0299851574bf0f5b69284bb554ef46b11dc73e9148e4bc75fdda4d2655bfda","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:09:15.586871Z","signature_b64":"9tYQ94fC3ASpAKVc+ab4NCcw15whQcBYR6FKShHiDfapasJeH4XVLRp5EyTuu+tfMTPDCQgWTx1+IeqJeFlVAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c0299851574bf0f5b69284bb554ef46b11dc73e9148e4bc75fdda4d2655bfda","last_reissued_at":"2026-07-05T04:09:15.586400Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:09:15.586400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.03012","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:09:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"424qqbcDb0mmnxMWH3BREbnc9kNA4VvR8V63SaRpdRKBxCwXPnqNIEVPS9L2OP/yzLX+dHVCZ1LS3LjzzbUnDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T20:16:50.513754Z"},"content_sha256":"ec4149142bef8a4540fc6d1338b372dc75b0212f12580abac2f7bc4d2b4e57b9","schema_version":"1.0","event_id":"sha256:ec4149142bef8a4540fc6d1338b372dc75b0212f12580abac2f7bc4d2b4e57b9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:DQBJTBIVOS7Q6W3JFBF3KVHPI2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Emphasis control for parallel neural TTS","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Dan Castellani, Jiangchuan Li, Shreyas Seshadri, Tuomo Raitio","submitted_at":"2021-10-06T18:45:39Z","abstract_excerpt":"Recent parallel neural text-to-speech (TTS) synthesis methods are able to generate speech with high fidelity while maintaining high performance. However, these systems often lack control over the output prosody, thus restricting the semantic information conveyable for a given text. This paper proposes a hierarchical parallel neural TTS system for prosodic emphasis control by learning a latent space that directly corresponds to a change in emphasis. Three candidate features for the latent space are compared: 1) Variance of pitch and duration within words in a sentence, 2) Wavelet-based feature "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03012","kind":"arxiv","version":2},"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/2110.03012/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:09:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AcVH8XlM9aaBdB+Fta7WQGfCDftgkWs7rw4F7qaNf9iGbCPxZq3NT9DgQFjYiMojvRGkClF0NWg5U0hvz+e4Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T20:16:50.514255Z"},"content_sha256":"602fd37a493e5ac8f3a45c503d1a4d38c31b0dd285d755325c479378d7703a25","schema_version":"1.0","event_id":"sha256:602fd37a493e5ac8f3a45c503d1a4d38c31b0dd285d755325c479378d7703a25"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DQBJTBIVOS7Q6W3JFBF3KVHPI2/bundle.json","state_url":"https://pith.science/pith/DQBJTBIVOS7Q6W3JFBF3KVHPI2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DQBJTBIVOS7Q6W3JFBF3KVHPI2/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":"2026-08-16T20:16:50Z","links":{"resolver":"https://pith.science/pith/DQBJTBIVOS7Q6W3JFBF3KVHPI2","bundle":"https://pith.science/pith/DQBJTBIVOS7Q6W3JFBF3KVHPI2/bundle.json","state":"https://pith.science/pith/DQBJTBIVOS7Q6W3JFBF3KVHPI2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DQBJTBIVOS7Q6W3JFBF3KVHPI2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:DQBJTBIVOS7Q6W3JFBF3KVHPI2","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":"9fd08b7c149f7050583c1a6649c2ef692f68f14e95291681609442578d9b0067","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-10-06T18:45:39Z","title_canon_sha256":"80e49dbdcc993b2f5692f141079c51177fac6ed4d039bde51b3ea33304606983"},"schema_version":"1.0","source":{"id":"2110.03012","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.03012","created_at":"2026-07-05T04:09:15Z"},{"alias_kind":"arxiv_version","alias_value":"2110.03012v2","created_at":"2026-07-05T04:09:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03012","created_at":"2026-07-05T04:09:15Z"},{"alias_kind":"pith_short_12","alias_value":"DQBJTBIVOS7Q","created_at":"2026-07-05T04:09:15Z"},{"alias_kind":"pith_short_16","alias_value":"DQBJTBIVOS7Q6W3J","created_at":"2026-07-05T04:09:15Z"},{"alias_kind":"pith_short_8","alias_value":"DQBJTBIV","created_at":"2026-07-05T04:09:15Z"}],"graph_snapshots":[{"event_id":"sha256:602fd37a493e5ac8f3a45c503d1a4d38c31b0dd285d755325c479378d7703a25","target":"graph","created_at":"2026-07-05T04:09:15Z","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/2110.03012/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent parallel neural text-to-speech (TTS) synthesis methods are able to generate speech with high fidelity while maintaining high performance. However, these systems often lack control over the output prosody, thus restricting the semantic information conveyable for a given text. This paper proposes a hierarchical parallel neural TTS system for prosodic emphasis control by learning a latent space that directly corresponds to a change in emphasis. Three candidate features for the latent space are compared: 1) Variance of pitch and duration within words in a sentence, 2) Wavelet-based feature ","authors_text":"Dan Castellani, Jiangchuan Li, Shreyas Seshadri, Tuomo Raitio","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-10-06T18:45:39Z","title":"Emphasis control for parallel neural TTS"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03012","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:ec4149142bef8a4540fc6d1338b372dc75b0212f12580abac2f7bc4d2b4e57b9","target":"record","created_at":"2026-07-05T04:09:15Z","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":"9fd08b7c149f7050583c1a6649c2ef692f68f14e95291681609442578d9b0067","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-10-06T18:45:39Z","title_canon_sha256":"80e49dbdcc993b2f5692f141079c51177fac6ed4d039bde51b3ea33304606983"},"schema_version":"1.0","source":{"id":"2110.03012","kind":"arxiv","version":2}},"canonical_sha256":"1c0299851574bf0f5b69284bb554ef46b11dc73e9148e4bc75fdda4d2655bfda","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c0299851574bf0f5b69284bb554ef46b11dc73e9148e4bc75fdda4d2655bfda","first_computed_at":"2026-07-05T04:09:15.586400Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:09:15.586400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9tYQ94fC3ASpAKVc+ab4NCcw15whQcBYR6FKShHiDfapasJeH4XVLRp5EyTuu+tfMTPDCQgWTx1+IeqJeFlVAg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:09:15.586871Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.03012","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec4149142bef8a4540fc6d1338b372dc75b0212f12580abac2f7bc4d2b4e57b9","sha256:602fd37a493e5ac8f3a45c503d1a4d38c31b0dd285d755325c479378d7703a25"],"state_sha256":"8a331775e91aa2f4dba609a17fc12759e23fbf2a8587dad036857945971a99cc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kDfLF242PSd20NaZfO88btL6cSVc2pOJNaBSrypIDhTRkEqO67SHA8mOkljecBCn53n1X9YboIlB43SrCJpsAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T20:16:50.518518Z","bundle_sha256":"41e50c27ed5ea4d4ad69a884b8c3faed574c06eb87c626f754aa1f6be12d910e"}}