{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:MHUEIDHMJFDSKDJMWQRBIDTHFU","short_pith_number":"pith:MHUEIDHM","canonical_record":{"source":{"id":"1702.07825","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-02-25T03:11:04Z","cross_cats_sorted":["cs.LG","cs.NE","cs.SD"],"title_canon_sha256":"83460e6e49d007d7567a66d2d28bc7ae2b04b2bf67f75846c49d5876122a4859","abstract_canon_sha256":"f2cb7c6ff6243b459b76c0306ba10c6d62ad8e5409f6a9b4135c55cbcb7f44b5"},"schema_version":"1.0"},"canonical_sha256":"61e8440cec4947250d2cb422140e672d2c7fb1cbd1f8cd34b1fe91c0b9189751","source":{"kind":"arxiv","id":"1702.07825","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.07825","created_at":"2026-05-18T00:49:06Z"},{"alias_kind":"arxiv_version","alias_value":"1702.07825v2","created_at":"2026-05-18T00:49:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.07825","created_at":"2026-05-18T00:49:06Z"},{"alias_kind":"pith_short_12","alias_value":"MHUEIDHMJFDS","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_16","alias_value":"MHUEIDHMJFDSKDJM","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_8","alias_value":"MHUEIDHM","created_at":"2026-05-18T12:31:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:MHUEIDHMJFDSKDJMWQRBIDTHFU","target":"record","payload":{"canonical_record":{"source":{"id":"1702.07825","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-02-25T03:11:04Z","cross_cats_sorted":["cs.LG","cs.NE","cs.SD"],"title_canon_sha256":"83460e6e49d007d7567a66d2d28bc7ae2b04b2bf67f75846c49d5876122a4859","abstract_canon_sha256":"f2cb7c6ff6243b459b76c0306ba10c6d62ad8e5409f6a9b4135c55cbcb7f44b5"},"schema_version":"1.0"},"canonical_sha256":"61e8440cec4947250d2cb422140e672d2c7fb1cbd1f8cd34b1fe91c0b9189751","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:06.228340Z","signature_b64":"o/XFB5mgfrdi6lqqadzxbzcnEv/R+CVLz1Tkzyy6nAWJg6TsMVzF8B0J4XRGDg6BRUCZuA+SGla9bThYeVbdDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61e8440cec4947250d2cb422140e672d2c7fb1cbd1f8cd34b1fe91c0b9189751","last_reissued_at":"2026-05-18T00:49:06.227845Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:06.227845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1702.07825","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":"2026-05-18T00:49:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QCZk4se37Nc9QGqfayvwsyjImfO9vyuXrtn7BciJZ4uyiqnt+KUodvktPPQfC5UUH/KCV5ZqY9+0ph/vs5kVBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:15:36.446887Z"},"content_sha256":"fe52377cf65e12eb8a1a59a2448d414326a5f687e62c90fa732a6b25179837bc","schema_version":"1.0","event_id":"sha256:fe52377cf65e12eb8a1a59a2448d414326a5f687e62c90fa732a6b25179837bc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:MHUEIDHMJFDSKDJMWQRBIDTHFU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Voice: Real-time Neural Text-to-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","cs.SD"],"primary_cat":"cs.CL","authors_text":"Adam Coates, Andrew Gibiansky, Andrew Ng, Gregory Diamos, John Miller, Jonathan Raiman, Mike Chrzanowski, Mohammad Shoeybi, Sercan O. Arik, Shubho Sengupta, Xian Li, Yongguo Kang","submitted_at":"2017-02-25T03:11:04Z","abstract_excerpt":"We present Deep Voice, a production-quality text-to-speech system constructed entirely from deep neural networks. Deep Voice lays the groundwork for truly end-to-end neural speech synthesis. The system comprises five major building blocks: a segmentation model for locating phoneme boundaries, a grapheme-to-phoneme conversion model, a phoneme duration prediction model, a fundamental frequency prediction model, and an audio synthesis model. For the segmentation model, we propose a novel way of performing phoneme boundary detection with deep neural networks using connectionist temporal classifica"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.07825","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":""},"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":"2026-05-18T00:49:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NtzhYLU2kPg7lYvwxZx6syPkslI1s+we/eQR3w8H3U4O7puRIGN/F+Mos9Rk3ZxkTwPpnlicuLNgZn235OQoAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:15:36.447567Z"},"content_sha256":"ead5574e258bc31c437b867395bf7b4c4f153f619e8bb5edbb99b9e2b34ee9b0","schema_version":"1.0","event_id":"sha256:ead5574e258bc31c437b867395bf7b4c4f153f619e8bb5edbb99b9e2b34ee9b0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MHUEIDHMJFDSKDJMWQRBIDTHFU/bundle.json","state_url":"https://pith.science/pith/MHUEIDHMJFDSKDJMWQRBIDTHFU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MHUEIDHMJFDSKDJMWQRBIDTHFU/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":"2026-05-25T19:15:36Z","links":{"resolver":"https://pith.science/pith/MHUEIDHMJFDSKDJMWQRBIDTHFU","bundle":"https://pith.science/pith/MHUEIDHMJFDSKDJMWQRBIDTHFU/bundle.json","state":"https://pith.science/pith/MHUEIDHMJFDSKDJMWQRBIDTHFU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MHUEIDHMJFDSKDJMWQRBIDTHFU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:MHUEIDHMJFDSKDJMWQRBIDTHFU","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":"f2cb7c6ff6243b459b76c0306ba10c6d62ad8e5409f6a9b4135c55cbcb7f44b5","cross_cats_sorted":["cs.LG","cs.NE","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-02-25T03:11:04Z","title_canon_sha256":"83460e6e49d007d7567a66d2d28bc7ae2b04b2bf67f75846c49d5876122a4859"},"schema_version":"1.0","source":{"id":"1702.07825","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.07825","created_at":"2026-05-18T00:49:06Z"},{"alias_kind":"arxiv_version","alias_value":"1702.07825v2","created_at":"2026-05-18T00:49:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.07825","created_at":"2026-05-18T00:49:06Z"},{"alias_kind":"pith_short_12","alias_value":"MHUEIDHMJFDS","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_16","alias_value":"MHUEIDHMJFDSKDJM","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_8","alias_value":"MHUEIDHM","created_at":"2026-05-18T12:31:31Z"}],"graph_snapshots":[{"event_id":"sha256:ead5574e258bc31c437b867395bf7b4c4f153f619e8bb5edbb99b9e2b34ee9b0","target":"graph","created_at":"2026-05-18T00:49:06Z","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":"We present Deep Voice, a production-quality text-to-speech system constructed entirely from deep neural networks. Deep Voice lays the groundwork for truly end-to-end neural speech synthesis. The system comprises five major building blocks: a segmentation model for locating phoneme boundaries, a grapheme-to-phoneme conversion model, a phoneme duration prediction model, a fundamental frequency prediction model, and an audio synthesis model. For the segmentation model, we propose a novel way of performing phoneme boundary detection with deep neural networks using connectionist temporal classifica","authors_text":"Adam Coates, Andrew Gibiansky, Andrew Ng, Gregory Diamos, John Miller, Jonathan Raiman, Mike Chrzanowski, Mohammad Shoeybi, Sercan O. Arik, Shubho Sengupta, Xian Li, Yongguo Kang","cross_cats":["cs.LG","cs.NE","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-02-25T03:11:04Z","title":"Deep Voice: Real-time Neural Text-to-Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.07825","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:fe52377cf65e12eb8a1a59a2448d414326a5f687e62c90fa732a6b25179837bc","target":"record","created_at":"2026-05-18T00:49:06Z","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":"f2cb7c6ff6243b459b76c0306ba10c6d62ad8e5409f6a9b4135c55cbcb7f44b5","cross_cats_sorted":["cs.LG","cs.NE","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-02-25T03:11:04Z","title_canon_sha256":"83460e6e49d007d7567a66d2d28bc7ae2b04b2bf67f75846c49d5876122a4859"},"schema_version":"1.0","source":{"id":"1702.07825","kind":"arxiv","version":2}},"canonical_sha256":"61e8440cec4947250d2cb422140e672d2c7fb1cbd1f8cd34b1fe91c0b9189751","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"61e8440cec4947250d2cb422140e672d2c7fb1cbd1f8cd34b1fe91c0b9189751","first_computed_at":"2026-05-18T00:49:06.227845Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:49:06.227845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o/XFB5mgfrdi6lqqadzxbzcnEv/R+CVLz1Tkzyy6nAWJg6TsMVzF8B0J4XRGDg6BRUCZuA+SGla9bThYeVbdDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:49:06.228340Z","signed_message":"canonical_sha256_bytes"},"source_id":"1702.07825","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe52377cf65e12eb8a1a59a2448d414326a5f687e62c90fa732a6b25179837bc","sha256:ead5574e258bc31c437b867395bf7b4c4f153f619e8bb5edbb99b9e2b34ee9b0"],"state_sha256":"6e7b8ce002f30b67513b17bc65c3b1486982effe2ccd53f9d375b77ff0da2494"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y7cZuEHNh44rmS22kvbHaWH5gOG3FpJctGlCYH9rxEjwiOOj3J/zKaCqRAvvzu2YlP3U6lUgHvRqQU+PjYdRAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T19:15:36.455984Z","bundle_sha256":"d41d4eef7bb10e8546776079bc7fc3b948e60c4c41dfe4d905aaeb8889d7bb19"}}