{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:GU3Y4K4VW5GKYIWT2DKTBIVJJ5","short_pith_number":"pith:GU3Y4K4V","canonical_record":{"source":{"id":"1710.07654","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2017-10-20T18:17:23Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","eess.AS"],"title_canon_sha256":"a9b19a224eea85de7a43b5a19f5e4233cffb1621e872bd3496dba64be0a733aa","abstract_canon_sha256":"6a1b06915a7ae47ee887a2f487b531ebae9ca04e90787983c633ffc73d3dc830"},"schema_version":"1.0"},"canonical_sha256":"35378e2b95b74cac22d3d0d530a2a94f7fa29653eaeb00fcc817629a20533b2a","source":{"kind":"arxiv","id":"1710.07654","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.07654","created_at":"2026-05-18T00:22:49Z"},{"alias_kind":"arxiv_version","alias_value":"1710.07654v3","created_at":"2026-05-18T00:22:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.07654","created_at":"2026-05-18T00:22:49Z"},{"alias_kind":"pith_short_12","alias_value":"GU3Y4K4VW5GK","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"GU3Y4K4VW5GKYIWT","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"GU3Y4K4V","created_at":"2026-05-18T12:31:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:GU3Y4K4VW5GKYIWT2DKTBIVJJ5","target":"record","payload":{"canonical_record":{"source":{"id":"1710.07654","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2017-10-20T18:17:23Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","eess.AS"],"title_canon_sha256":"a9b19a224eea85de7a43b5a19f5e4233cffb1621e872bd3496dba64be0a733aa","abstract_canon_sha256":"6a1b06915a7ae47ee887a2f487b531ebae9ca04e90787983c633ffc73d3dc830"},"schema_version":"1.0"},"canonical_sha256":"35378e2b95b74cac22d3d0d530a2a94f7fa29653eaeb00fcc817629a20533b2a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:49.203480Z","signature_b64":"gLIhWoFr/d6u1dAFXsgXDGJ2VK06WYMZ2f5rFlxzmDXvn72m35NdfAPej4jfKGRQcwFvoZuSaTAN1+tY9X4yDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35378e2b95b74cac22d3d0d530a2a94f7fa29653eaeb00fcc817629a20533b2a","last_reissued_at":"2026-05-18T00:22:49.203018Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:49.203018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1710.07654","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":"2026-05-18T00:22:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H7ltOKKqIZrz4Zcq9tTMV6rWcN9yj5wBxWtSkqDk2cSliJwtXhnSJPT1Foqn49vgZkgzsAfjnufk2Z29eTH7BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T17:09:06.987821Z"},"content_sha256":"9b8b1a0351ce5cc4bdb2db4a71b8b60010f68b0b1e27f2729d798ff5e2c63666","schema_version":"1.0","event_id":"sha256:9b8b1a0351ce5cc4bdb2db4a71b8b60010f68b0b1e27f2729d798ff5e2c63666"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:GU3Y4K4VW5GKYIWT2DKTBIVJJ5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ajay Kannan, Andrew Gibiansky, John Miller, Jonathan Raiman, Kainan Peng, Sercan O. Arik, Sharan Narang, Wei Ping","submitted_at":"2017-10-20T18:17:23Z","abstract_excerpt":"We present Deep Voice 3, a fully-convolutional attention-based neural text-to-speech (TTS) system. Deep Voice 3 matches state-of-the-art neural speech synthesis systems in naturalness while training ten times faster. We scale Deep Voice 3 to data set sizes unprecedented for TTS, training on more than eight hundred hours of audio from over two thousand speakers. In addition, we identify common error modes of attention-based speech synthesis networks, demonstrate how to mitigate them, and compare several different waveform synthesis methods. We also describe how to scale inference to ten million"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.07654","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":"2026-05-18T00:22:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R8f1G64tI3EK+iF6+np8ZMhy3MKLYFEQMMOvDfm0aR0Cy9zSghjzI+LeCMPnbypLLdUmfqj5nDAZetxqtsmZBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T17:09:06.988160Z"},"content_sha256":"b5bbd72827249c7d6f9276e2654a543f31b67a08ef6cc8a5e4a45639fe6d9762","schema_version":"1.0","event_id":"sha256:b5bbd72827249c7d6f9276e2654a543f31b67a08ef6cc8a5e4a45639fe6d9762"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GU3Y4K4VW5GKYIWT2DKTBIVJJ5/bundle.json","state_url":"https://pith.science/pith/GU3Y4K4VW5GKYIWT2DKTBIVJJ5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GU3Y4K4VW5GKYIWT2DKTBIVJJ5/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":"2026-06-01T17:09:06Z","links":{"resolver":"https://pith.science/pith/GU3Y4K4VW5GKYIWT2DKTBIVJJ5","bundle":"https://pith.science/pith/GU3Y4K4VW5GKYIWT2DKTBIVJJ5/bundle.json","state":"https://pith.science/pith/GU3Y4K4VW5GKYIWT2DKTBIVJJ5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GU3Y4K4VW5GKYIWT2DKTBIVJJ5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:GU3Y4K4VW5GKYIWT2DKTBIVJJ5","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":"6a1b06915a7ae47ee887a2f487b531ebae9ca04e90787983c633ffc73d3dc830","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2017-10-20T18:17:23Z","title_canon_sha256":"a9b19a224eea85de7a43b5a19f5e4233cffb1621e872bd3496dba64be0a733aa"},"schema_version":"1.0","source":{"id":"1710.07654","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.07654","created_at":"2026-05-18T00:22:49Z"},{"alias_kind":"arxiv_version","alias_value":"1710.07654v3","created_at":"2026-05-18T00:22:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.07654","created_at":"2026-05-18T00:22:49Z"},{"alias_kind":"pith_short_12","alias_value":"GU3Y4K4VW5GK","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"GU3Y4K4VW5GKYIWT","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"GU3Y4K4V","created_at":"2026-05-18T12:31:18Z"}],"graph_snapshots":[{"event_id":"sha256:b5bbd72827249c7d6f9276e2654a543f31b67a08ef6cc8a5e4a45639fe6d9762","target":"graph","created_at":"2026-05-18T00:22:49Z","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":"We present Deep Voice 3, a fully-convolutional attention-based neural text-to-speech (TTS) system. Deep Voice 3 matches state-of-the-art neural speech synthesis systems in naturalness while training ten times faster. We scale Deep Voice 3 to data set sizes unprecedented for TTS, training on more than eight hundred hours of audio from over two thousand speakers. In addition, we identify common error modes of attention-based speech synthesis networks, demonstrate how to mitigate them, and compare several different waveform synthesis methods. We also describe how to scale inference to ten million","authors_text":"Ajay Kannan, Andrew Gibiansky, John Miller, Jonathan Raiman, Kainan Peng, Sercan O. Arik, Sharan Narang, Wei Ping","cross_cats":["cs.AI","cs.CL","cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2017-10-20T18:17:23Z","title":"Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.07654","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":"sha256:9b8b1a0351ce5cc4bdb2db4a71b8b60010f68b0b1e27f2729d798ff5e2c63666","target":"record","created_at":"2026-05-18T00:22:49Z","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":"6a1b06915a7ae47ee887a2f487b531ebae9ca04e90787983c633ffc73d3dc830","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2017-10-20T18:17:23Z","title_canon_sha256":"a9b19a224eea85de7a43b5a19f5e4233cffb1621e872bd3496dba64be0a733aa"},"schema_version":"1.0","source":{"id":"1710.07654","kind":"arxiv","version":3}},"canonical_sha256":"35378e2b95b74cac22d3d0d530a2a94f7fa29653eaeb00fcc817629a20533b2a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35378e2b95b74cac22d3d0d530a2a94f7fa29653eaeb00fcc817629a20533b2a","first_computed_at":"2026-05-18T00:22:49.203018Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:49.203018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gLIhWoFr/d6u1dAFXsgXDGJ2VK06WYMZ2f5rFlxzmDXvn72m35NdfAPej4jfKGRQcwFvoZuSaTAN1+tY9X4yDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:49.203480Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.07654","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9b8b1a0351ce5cc4bdb2db4a71b8b60010f68b0b1e27f2729d798ff5e2c63666","sha256:b5bbd72827249c7d6f9276e2654a543f31b67a08ef6cc8a5e4a45639fe6d9762"],"state_sha256":"2fcd2594b106d674a9ed472076b0071592298aae4f204424bf29d798a5795113"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1BhW3Af5ejWeWukKESjHXi91jh+9ZzAATKp383yn9fQLfsaxS4KPiGkYUygsWN9qH2yhbzuIehmaYeGweYbLCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T17:09:06.990148Z","bundle_sha256":"4a1d7322640ebdecfc6433dbb6a1a93304340b8304d0d65a4756eb235fbabd6e"}}