{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:MHUEIDHMJFDSKDJMWQRBIDTHFU","short_pith_number":"pith:MHUEIDHM","schema_version":"1.0","canonical_sha256":"61e8440cec4947250d2cb422140e672d2c7fb1cbd1f8cd34b1fe91c0b9189751","source":{"kind":"arxiv","id":"1702.07825","version":2},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1702.07825","created_at":"2026-05-18T00:49:06.227916+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.07825v2","created_at":"2026-05-18T00:49:06.227916+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.07825","created_at":"2026-05-18T00:49:06.227916+00:00"},{"alias_kind":"pith_short_12","alias_value":"MHUEIDHMJFDS","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_16","alias_value":"MHUEIDHMJFDSKDJM","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_8","alias_value":"MHUEIDHM","created_at":"2026-05-18T12:31:31.346846+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"1907.01749","citing_title":"Polyphone Disambiguation for Mandarin Chinese Using Conditional Neural Network with Multi-level Embedding Features","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"1907.02784","citing_title":"A Methodology for Controlling the Emotional Expressiveness in Synthetic Speech -- a Deep Learning approach","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"1907.07769","citing_title":"Hierarchical Sequence to Sequence Voice Conversion with Limited Data","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MHUEIDHMJFDSKDJMWQRBIDTHFU","json":"https://pith.science/pith/MHUEIDHMJFDSKDJMWQRBIDTHFU.json","graph_json":"https://pith.science/api/pith-number/MHUEIDHMJFDSKDJMWQRBIDTHFU/graph.json","events_json":"https://pith.science/api/pith-number/MHUEIDHMJFDSKDJMWQRBIDTHFU/events.json","paper":"https://pith.science/paper/MHUEIDHM"},"agent_actions":{"view_html":"https://pith.science/pith/MHUEIDHMJFDSKDJMWQRBIDTHFU","download_json":"https://pith.science/pith/MHUEIDHMJFDSKDJMWQRBIDTHFU.json","view_paper":"https://pith.science/paper/MHUEIDHM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.07825&json=true","fetch_graph":"https://pith.science/api/pith-number/MHUEIDHMJFDSKDJMWQRBIDTHFU/graph.json","fetch_events":"https://pith.science/api/pith-number/MHUEIDHMJFDSKDJMWQRBIDTHFU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MHUEIDHMJFDSKDJMWQRBIDTHFU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MHUEIDHMJFDSKDJMWQRBIDTHFU/action/storage_attestation","attest_author":"https://pith.science/pith/MHUEIDHMJFDSKDJMWQRBIDTHFU/action/author_attestation","sign_citation":"https://pith.science/pith/MHUEIDHMJFDSKDJMWQRBIDTHFU/action/citation_signature","submit_replication":"https://pith.science/pith/MHUEIDHMJFDSKDJMWQRBIDTHFU/action/replication_record"}},"created_at":"2026-05-18T00:49:06.227916+00:00","updated_at":"2026-05-18T00:49:06.227916+00:00"}